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

Dataset: Open Web Text

Neuron 1227 in Layer 1

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: 3.6224. Min Range: -3.6224

Max Act: 3.6224. Min Act: -0.1700

Data Index: 4255677 (Open Web Text)

Max Activating Token Index: 119

Text #1

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.5460. Min Act: -0.1700

Data Index: 6563021 (Open Web Text)

Max Activating Token Index: 218

Text #2

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4843. Min Act: -0.1700

Data Index: 2077068 (Open Web Text)

Max Activating Token Index: 80

Text #3

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4947. Min Act: -0.1700

Data Index: 799130 (Open Web Text)

Max Activating Token Index: 437

Text #4

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4606. Min Act: -0.1700

Data Index: 1803153 (Open Web Text)

Max Activating Token Index: 294

Text #5

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4641. Min Act: -0.1700

Data Index: 7060832 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4276. Min Act: -0.1700

Data Index: 7371420 (Open Web Text)

Max Activating Token Index: 52

Text #7

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4377. Min Act: -0.1700

Data Index: 8282287 (Open Web Text)

Max Activating Token Index: 322

Text #8

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4138. Min Act: -0.1700

Data Index: 434862 (Open Web Text)

Max Activating Token Index: 99

Text #9

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4022. Min Act: -0.1700

Data Index: 4054391 (Open Web Text)

Max Activating Token Index: 108

Text #10

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4059. Min Act: -0.1700

Data Index: 966075 (Open Web Text)

Max Activating Token Index: 653

Text #11

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4027. Min Act: -0.1700

Data Index: 2077066 (Open Web Text)

Max Activating Token Index: 240

Text #12

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3953. Min Act: -0.1700

Data Index: 8673832 (Open Web Text)

Max Activating Token Index: 253

Text #13

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4017. Min Act: -0.1700

Data Index: 1308419 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3830. Min Act: -0.1700

Data Index: 3842369 (Open Web Text)

Max Activating Token Index: 93

Text #15

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3920. Min Act: -0.1700

Data Index: 4562318 (Open Web Text)

Max Activating Token Index: 365

Text #16

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3915. Min Act: -0.1700

Data Index: 4332886 (Open Web Text)

Max Activating Token Index: 504

Text #17

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3865. Min Act: -0.1700

Data Index: 5008227 (Open Web Text)

Max Activating Token Index: 67

Text #18

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3852. Min Act: -0.1700

Data Index: 3791290 (Open Web Text)

Max Activating Token Index: 562

Text #19

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3813. Min Act: -0.1700

Data Index: 979520 (Open Web Text)

Max Activating Token Index: 476