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

Dataset: Open Web Text

Neuron 492 in Layer 0

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: 1.5181. Min Range: -1.5181

Max Act: 1.5181. Min Act: -0.1223

Data Index: 6077046 (Open Web Text)

Max Activating Token Index: 258

Text #1

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4999. Min Act: -0.0699

Data Index: 6881917 (Open Web Text)

Max Activating Token Index: 210

Text #2

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.5037. Min Act: -0.1478

Data Index: 456243 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4828. Min Act: -0.0635

Data Index: 4622880 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4806. Min Act: -0.0460

Data Index: 4620647 (Open Web Text)

Max Activating Token Index: 659

Text #5

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4723. Min Act: -0.0422

Data Index: 5322234 (Open Web Text)

Max Activating Token Index: 1018

Text #6

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4556. Min Act: -0.0455

Data Index: 8737535 (Open Web Text)

Max Activating Token Index: 945

Text #7

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4584. Min Act: -0.1612

Data Index: 218541 (Open Web Text)

Max Activating Token Index: 156

Text #8

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4505. Min Act: -0.0749

Data Index: 7899479 (Open Web Text)

Max Activating Token Index: 631

Text #9

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4543. Min Act: -0.0886

Data Index: 1638248 (Open Web Text)

Max Activating Token Index: 886

Text #10

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4468. Min Act: -0.1225

Data Index: 7237250 (Open Web Text)

Max Activating Token Index: 1016

Text #11

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4446. Min Act: -0.0439

Data Index: 7729674 (Open Web Text)

Max Activating Token Index: 485

Text #12

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4485. Min Act: -0.1222

Data Index: 5675846 (Open Web Text)

Max Activating Token Index: 234

Text #13

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4368. Min Act: -0.0652

Data Index: 6826036 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4381. Min Act: -0.1166

Data Index: 6695485 (Open Web Text)

Max Activating Token Index: 735

Text #15

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4252. Min Act: -0.1671

Data Index: 5130797 (Open Web Text)

Max Activating Token Index: 977

Text #16

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4383. Min Act: -0.0922

Data Index: 979347 (Open Web Text)

Max Activating Token Index: 656

Text #17

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4385. Min Act: -0.0989

Data Index: 4061479 (Open Web Text)

Max Activating Token Index: 774

Text #18

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4311. Min Act: -0.1072

Data Index: 3981383 (Open Web Text)

Max Activating Token Index: 313

Text #19

Max Range: 1.5181. Min Range: -1.5181

Max Act: 1.4273. Min Act: -0.0832

Data Index: 1300536 (Open Web Text)

Max Activating Token Index: 680