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

Dataset: Open Web Text

Neuron 188 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: 1.9154. Min Range: -1.9154

Max Act: 1.9154. Min Act: -0.1699

Data Index: 2661880 (Open Web Text)

Max Activating Token Index: 635

Text #1

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.9060. Min Act: -0.1700

Data Index: 1667066 (Open Web Text)

Max Activating Token Index: 224

Text #2

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8568. Min Act: -0.1700

Data Index: 3857359 (Open Web Text)

Max Activating Token Index: 578

Text #3

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8557. Min Act: -0.1700

Data Index: 2095153 (Open Web Text)

Max Activating Token Index: 673

Text #4

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8468. Min Act: -0.1700

Data Index: 8573155 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8503. Min Act: -0.1700

Data Index: 2552117 (Open Web Text)

Max Activating Token Index: 367

Text #6

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8243. Min Act: -0.1700

Data Index: 5245549 (Open Web Text)

Max Activating Token Index: 408

Text #7

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8215. Min Act: -0.1699

Data Index: 2536738 (Open Web Text)

Max Activating Token Index: 67

Text #8

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8196. Min Act: -0.1700

Data Index: 6288525 (Open Web Text)

Max Activating Token Index: 939

Text #9

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8181. Min Act: -0.1695

Data Index: 4900643 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8011. Min Act: -0.1700

Data Index: 2734876 (Open Web Text)

Max Activating Token Index: 183

Text #11

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8109. Min Act: -0.1700

Data Index: 5597059 (Open Web Text)

Max Activating Token Index: 284

Text #12

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8068. Min Act: -0.1700

Data Index: 3368016 (Open Web Text)

Max Activating Token Index: 165

Text #13

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8096. Min Act: -0.1700

Data Index: 3974125 (Open Web Text)

Max Activating Token Index: 88

Text #14

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8231. Min Act: -0.1699

Data Index: 1102549 (Open Web Text)

Max Activating Token Index: 101

Text #15

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8189. Min Act: -0.1700

Data Index: 1076334 (Open Web Text)

Max Activating Token Index: 621

Text #16

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8007. Min Act: -0.1700

Data Index: 7053042 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8086. Min Act: -0.1699

Data Index: 2059412 (Open Web Text)

Max Activating Token Index: 368

Text #18

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8039. Min Act: -0.1700

Data Index: 6152477 (Open Web Text)

Max Activating Token Index: 596

Text #19

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8063. Min Act: -0.1700

Data Index: 6574630 (Open Web Text)

Max Activating Token Index: 658