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

Dataset: Open Web Text

Neuron 1676 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: 2.9132. Min Range: -2.9132

Max Act: 2.9080. Min Act: -0.1700

Data Index: 7548160 (Open Web Text)

Max Activating Token Index: 979

Text #1

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.9087. Min Act: -0.1700

Data Index: 2802393 (Open Web Text)

Max Activating Token Index: 747

Text #2

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.9132. Min Act: -0.1700

Data Index: 1595399 (Open Web Text)

Max Activating Token Index: 47

Text #3

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8842. Min Act: -0.1700

Data Index: 2993522 (Open Web Text)

Max Activating Token Index: 243

Text #4

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8749. Min Act: -0.1700

Data Index: 2997981 (Open Web Text)

Max Activating Token Index: 122

Text #5

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8762. Min Act: -0.1700

Data Index: 7368826 (Open Web Text)

Max Activating Token Index: 350

Text #6

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8544. Min Act: -0.1700

Data Index: 626152 (Open Web Text)

Max Activating Token Index: 205

Text #7

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8509. Min Act: -0.1700

Data Index: 637870 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8549. Min Act: -0.1700

Data Index: 1300181 (Open Web Text)

Max Activating Token Index: 839

Text #9

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8242. Min Act: -0.1700

Data Index: 2068595 (Open Web Text)

Max Activating Token Index: 479

Text #10

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8577. Min Act: -0.1700

Data Index: 8223295 (Open Web Text)

Max Activating Token Index: 311

Text #11

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8517. Min Act: -0.1700

Data Index: 510453 (Open Web Text)

Max Activating Token Index: 496

Text #12

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8536. Min Act: -0.1700

Data Index: 2401244 (Open Web Text)

Max Activating Token Index: 600

Text #13

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8374. Min Act: -0.1700

Data Index: 552995 (Open Web Text)

Max Activating Token Index: 335

Text #14

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8175. Min Act: -0.1700

Data Index: 5425981 (Open Web Text)

Max Activating Token Index: 160

Text #15

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8262. Min Act: -0.1700

Data Index: 1109261 (Open Web Text)

Max Activating Token Index: 632

Text #16

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8390. Min Act: -0.1700

Data Index: 4686233 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8418. Min Act: -0.1700

Data Index: 3084227 (Open Web Text)

Max Activating Token Index: 73

Text #18

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8452. Min Act: -0.1700

Data Index: 2424036 (Open Web Text)

Max Activating Token Index: 418

Text #19

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8217. Min Act: -0.1700

Data Index: 3784702 (Open Web Text)

Max Activating Token Index: 327