< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2660 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.3717. Min Act: -0.1700

Data Index: 1495143 (Open Web Text)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.3649. Min Act: -0.1700

Data Index: 6109805 (Open Web Text)

Max Activating Token Index: 702

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.3253. Min Act: -0.1700

Data Index: 6103826 (Open Web Text)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.3333. Min Act: -0.1700

Data Index: 5511101 (Open Web Text)

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.2947. Min Act: -0.1700

Data Index: 6857137 (Open Web Text)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.3165. Min Act: -0.1700

Data Index: 6312848 (Open Web Text)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.2988. Min Act: -0.1700

Data Index: 4164166 (Open Web Text)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.3207. Min Act: -0.1700

Data Index: 4119494 (Open Web Text)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.3248. Min Act: -0.1700

Data Index: 3973525 (Open Web Text)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.3097. Min Act: -0.1700

Data Index: 8461939 (Open Web Text)

Max Activating Token Index: 378

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.2997. Min Act: -0.1700

Data Index: 2280271 (Open Web Text)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.3044. Min Act: -0.1700

Data Index: 7858417 (Open Web Text)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.2934. Min Act: -0.1700

Data Index: 59404 (Open Web Text)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.2856. Min Act: -0.1700

Data Index: 8593605 (Open Web Text)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.2911. Min Act: -0.1700

Data Index: 1705725 (Open Web Text)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.2833. Min Act: -0.1700

Data Index: 3427170 (Open Web Text)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.2845. Min Act: -0.1700

Data Index: 1069829 (Open Web Text)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.2874. Min Act: -0.1700

Data Index: 7086599 (Open Web Text)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.2586. Min Act: -0.1700

Data Index: 1911289 (Open Web Text)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3717. Min Range: -2.3717

Max Act: 2.2620. Min Act: -0.1700

Data Index: 3058899 (Open Web Text)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #19