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

Dataset: Open Web Text

Neuron 157 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: 3.2176. Min Range: -3.2176

Max Act: 3.2176. Min Act: -0.1700

Data Index: 2417192 (Open Web Text)

Max Activating Token Index: 585

Text #1

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.1872. Min Act: -0.1700

Data Index: 5286162 (Open Web Text)

Max Activating Token Index: 97

Text #2

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.1764. Min Act: -0.1700

Data Index: 78089 (Open Web Text)

Max Activating Token Index: 738

Text #3

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.1721. Min Act: -0.1700

Data Index: 3865570 (Open Web Text)

Max Activating Token Index: 430

Text #4

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.1577. Min Act: -0.1700

Data Index: 7013581 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.1249. Min Act: -0.1700

Data Index: 5993939 (Open Web Text)

Max Activating Token Index: 305

Text #6

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.1377. Min Act: -0.1700

Data Index: 6123827 (Open Web Text)

Max Activating Token Index: 918

Text #7

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.1247. Min Act: -0.1700

Data Index: 8314825 (Open Web Text)

Max Activating Token Index: 360

Text #8

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.0911. Min Act: -0.1700

Data Index: 3997977 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.1264. Min Act: -0.1700

Data Index: 7316882 (Open Web Text)

Max Activating Token Index: 543

Text #10

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.0583. Min Act: -0.1700

Data Index: 6673400 (Open Web Text)

Max Activating Token Index: 967

Text #11

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.0758. Min Act: -0.1700

Data Index: 1687557 (Open Web Text)

Max Activating Token Index: 400

Text #12

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.0883. Min Act: -0.1700

Data Index: 5751146 (Open Web Text)

Max Activating Token Index: 313

Text #13

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.0761. Min Act: -0.1700

Data Index: 734338 (Open Web Text)

Max Activating Token Index: 272

Text #14

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.0465. Min Act: -0.1700

Data Index: 3118310 (Open Web Text)

Max Activating Token Index: 366

Text #15

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.0825. Min Act: -0.1700

Data Index: 3105323 (Open Web Text)

Max Activating Token Index: 895

Text #16

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.0328. Min Act: -0.1700

Data Index: 4196351 (Open Web Text)

Max Activating Token Index: 203

Text #17

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.0103. Min Act: -0.1700

Data Index: 7775143 (Open Web Text)

Max Activating Token Index: 300

Text #18

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.0257. Min Act: -0.1700

Data Index: 5806723 (Open Web Text)

Max Activating Token Index: 224

Text #19

Max Range: 3.2176. Min Range: -3.2176

Max Act: 3.0076. Min Act: -0.1700

Data Index: 7114726 (Open Web Text)

Max Activating Token Index: 313