< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 708 in Layer 3

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: 2.3450. Min Range: -2.3450

Max Act: 2.3372. Min Act: -0.1700

Data Index: 3222626 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.3450. Min Act: -0.1700

Data Index: 4241648 (Open Web Text)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.3103. Min Act: -0.1700

Data Index: 3894721 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2656. Min Act: -0.1700

Data Index: 2886818 (Open Web Text)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2545. Min Act: -0.1700

Data Index: 7843894 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2448. Min Act: -0.1700

Data Index: 8225869 (Open Web Text)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2404. Min Act: -0.1700

Data Index: 5329478 (Open Web Text)

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2411. Min Act: -0.1700

Data Index: 7452238 (Open Web Text)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2352. Min Act: -0.1700

Data Index: 7434268 (Open Web Text)

Max Activating Token Index: 816

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2464. Min Act: -0.1700

Data Index: 7428579 (Open Web Text)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2235. Min Act: -0.1700

Data Index: 161089 (Open Web Text)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2283. Min Act: -0.1700

Data Index: 1633985 (Open Web Text)

Max Activating Token Index: 371

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2226. Min Act: -0.1700

Data Index: 7796212 (Open Web Text)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2245. Min Act: -0.1700

Data Index: 7905499 (Open Web Text)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2313. Min Act: -0.1700

Data Index: 2719734 (Open Web Text)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2079. Min Act: -0.1700

Data Index: 3853226 (Open Web Text)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.1966. Min Act: -0.1700

Data Index: 1487438 (Open Web Text)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2015. Min Act: -0.1700

Data Index: 546856 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2071. Min Act: -0.1700

Data Index: 6730658 (Open Web Text)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3450. Min Range: -2.3450

Max Act: 2.2044. Min Act: -0.1700

Data Index: 2069466 (Open Web Text)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #19