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

Dataset: Open Web Text

Neuron 2937 in Layer 4

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: 3.1208. Min Range: -3.1208

Max Act: 3.1208. Min Act: -0.1700

Data Index: 6299058 (Open Web Text)

Max Activating Token Index: 575

Text #1

Max Range: 3.1208. Min Range: -3.1208

Max Act: 3.0159. Min Act: -0.1700

Data Index: 5350452 (Open Web Text)

Max Activating Token Index: 41

Text #2

Max Range: 3.1208. Min Range: -3.1208

Max Act: 3.0074. Min Act: -0.1700

Data Index: 1467075 (Open Web Text)

Max Activating Token Index: 274

Text #3

Max Range: 3.1208. Min Range: -3.1208

Max Act: 3.0141. Min Act: -0.1700

Data Index: 5442490 (Open Web Text)

Max Activating Token Index: 304

Text #4

Max Range: 3.1208. Min Range: -3.1208

Max Act: 3.0203. Min Act: -0.1700

Data Index: 7658539 (Open Web Text)

Max Activating Token Index: 638

Text #5

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9810. Min Act: -0.1700

Data Index: 5327266 (Open Web Text)

Max Activating Token Index: 315

Text #6

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9615. Min Act: -0.1700

Data Index: 5979744 (Open Web Text)

Max Activating Token Index: 439

Text #7

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9577. Min Act: -0.1700

Data Index: 335126 (Open Web Text)

Max Activating Token Index: 926

Text #8

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9626. Min Act: -0.1700

Data Index: 5454412 (Open Web Text)

Max Activating Token Index: 542

Text #9

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9520. Min Act: -0.1700

Data Index: 1051044 (Open Web Text)

Max Activating Token Index: 1019

Text #10

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9657. Min Act: -0.1700

Data Index: 5317646 (Open Web Text)

Max Activating Token Index: 484

Text #11

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9816. Min Act: -0.1700

Data Index: 2144492 (Open Web Text)

Max Activating Token Index: 593

Text #12

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9700. Min Act: -0.1700

Data Index: 5703208 (Open Web Text)

Max Activating Token Index: 198

Text #13

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9570. Min Act: -0.1700

Data Index: 1071923 (Open Web Text)

Max Activating Token Index: 766

Text #14

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9510. Min Act: -0.1700

Data Index: 6345112 (Open Web Text)

Max Activating Token Index: 324

Text #15

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9505. Min Act: -0.1700

Data Index: 1683173 (Open Web Text)

Max Activating Token Index: 262

Text #16

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9340. Min Act: -0.1700

Data Index: 5206192 (Open Web Text)

Max Activating Token Index: 735

Text #17

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9476. Min Act: -0.1700

Data Index: 2287608 (Open Web Text)

Max Activating Token Index: 401

Text #18

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9079. Min Act: -0.1700

Data Index: 727924 (Open Web Text)

Max Activating Token Index: 777

Text #19

Max Range: 3.1208. Min Range: -3.1208

Max Act: 2.9371. Min Act: -0.1700

Data Index: 2003991 (Open Web Text)

Max Activating Token Index: 358