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

Dataset: Open Web Text

Neuron 2605 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: 3.6807. Min Range: -3.6807

Max Act: 3.6807. Min Act: -0.1700

Data Index: 733762 (Open Web Text)

Max Activating Token Index: 385

Text #1

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.6651. Min Act: -0.1700

Data Index: 7878601 (Open Web Text)

Max Activating Token Index: 225

Text #2

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.6347. Min Act: -0.1700

Data Index: 5607835 (Open Web Text)

Max Activating Token Index: 202

Text #3

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5949. Min Act: -0.1700

Data Index: 513719 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.6053. Min Act: -0.1700

Data Index: 7229890 (Open Web Text)

Max Activating Token Index: 262

Text #5

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5877. Min Act: -0.1700

Data Index: 7920421 (Open Web Text)

Max Activating Token Index: 65

Text #6

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.6075. Min Act: -0.1700

Data Index: 298474 (Open Web Text)

Max Activating Token Index: 320

Text #7

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5893. Min Act: -0.1700

Data Index: 1289201 (Open Web Text)

Max Activating Token Index: 562

Text #8

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5741. Min Act: -0.1700

Data Index: 5176615 (Open Web Text)

Max Activating Token Index: 602

Text #9

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5929. Min Act: -0.1700

Data Index: 1694462 (Open Web Text)

Max Activating Token Index: 487

Text #10

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5926. Min Act: -0.1700

Data Index: 1921407 (Open Web Text)

Max Activating Token Index: 329

Text #11

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5831. Min Act: -0.1700

Data Index: 2115307 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5611. Min Act: -0.1700

Data Index: 7411266 (Open Web Text)

Max Activating Token Index: 401

Text #13

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5593. Min Act: -0.1700

Data Index: 7331059 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5447. Min Act: -0.1700

Data Index: 5284555 (Open Web Text)

Max Activating Token Index: 179

Text #15

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5513. Min Act: -0.1700

Data Index: 2814047 (Open Web Text)

Max Activating Token Index: 135

Text #16

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5580. Min Act: -0.1700

Data Index: 1417654 (Open Web Text)

Max Activating Token Index: 50

Text #17

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5369. Min Act: -0.1700

Data Index: 7780642 (Open Web Text)

Max Activating Token Index: 386

Text #18

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5535. Min Act: -0.1700

Data Index: 7015291 (Open Web Text)

Max Activating Token Index: 80

Text #19

Max Range: 3.6807. Min Range: -3.6807

Max Act: 3.5367. Min Act: -0.1700

Data Index: 4074124 (Open Web Text)

Max Activating Token Index: 90