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

Dataset: Open Web Text

Neuron 2777 in Layer 0

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: 4.4001. Min Range: -4.4001

Max Act: 4.4001. Min Act: -0.1700

Data Index: 314381 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.3381. Min Act: -0.1700

Data Index: 6683683 (Open Web Text)

Max Activating Token Index: 36

Text #2

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.3503. Min Act: -0.1700

Data Index: 3514941 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.3275. Min Act: -0.1700

Data Index: 377664 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.3159. Min Act: -0.1700

Data Index: 3890317 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.3166. Min Act: -0.1700

Data Index: 903820 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.2675. Min Act: -0.1700

Data Index: 6781113 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.2550. Min Act: -0.1700

Data Index: 5456288 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.2468. Min Act: -0.1700

Data Index: 5472052 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.2251. Min Act: -0.1700

Data Index: 1064536 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.2486. Min Act: -0.1700

Data Index: 261745 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.2273. Min Act: -0.1700

Data Index: 2453652 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.2238. Min Act: -0.1700

Data Index: 2055198 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.2484. Min Act: -0.1700

Data Index: 3853924 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.1983. Min Act: -0.1700

Data Index: 4369882 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.2116. Min Act: -0.1700

Data Index: 4953284 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.2018. Min Act: -0.1700

Data Index: 4072615 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.1966. Min Act: -0.1700

Data Index: 2595510 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.1984. Min Act: -0.1700

Data Index: 4954588 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.4001. Min Range: -4.4001

Max Act: 4.1993. Min Act: -0.1700

Data Index: 1237738 (Open Web Text)

Max Activating Token Index: 3