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

Dataset: Open Web Text

Neuron 1336 in Layer 6

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: 3.9127. Min Range: -3.9127

Max Act: 3.9127. Min Act: -0.1700

Data Index: 6483652 (Open Web Text)

Max Activating Token Index: 635

Text #1

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.8339. Min Act: -0.1700

Data Index: 240876 (Open Web Text)

Max Activating Token Index: 661

Text #2

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.7117. Min Act: -0.1700

Data Index: 7698540 (Open Web Text)

Max Activating Token Index: 316

Text #3

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.6941. Min Act: -0.1700

Data Index: 1000932 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.6637. Min Act: -0.1700

Data Index: 6084620 (Open Web Text)

Max Activating Token Index: 928

Text #5

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.6404. Min Act: -0.1700

Data Index: 3871045 (Open Web Text)

Max Activating Token Index: 1009

Text #6

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.5959. Min Act: -0.1700

Data Index: 5767039 (Open Web Text)

Max Activating Token Index: 941

Text #7

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.6171. Min Act: -0.1700

Data Index: 2785931 (Open Web Text)

Max Activating Token Index: 394

Text #8

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.6065. Min Act: -0.1700

Data Index: 5576569 (Open Web Text)

Max Activating Token Index: 686

Text #9

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.6040. Min Act: -0.1700

Data Index: 561973 (Open Web Text)

Max Activating Token Index: 410

Text #10

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.5842. Min Act: -0.1700

Data Index: 4186261 (Open Web Text)

Max Activating Token Index: 736

Text #11

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.5450. Min Act: -0.1700

Data Index: 6784412 (Open Web Text)

Max Activating Token Index: 626

Text #12

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.5484. Min Act: -0.1700

Data Index: 2606436 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.5556. Min Act: -0.1700

Data Index: 232416 (Open Web Text)

Max Activating Token Index: 894

Text #14

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.5636. Min Act: -0.1700

Data Index: 6973519 (Open Web Text)

Max Activating Token Index: 218

Text #15

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.5645. Min Act: -0.1700

Data Index: 6287339 (Open Web Text)

Max Activating Token Index: 353

Text #16

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.5313. Min Act: -0.1700

Data Index: 7060867 (Open Web Text)

Max Activating Token Index: 807

Text #17

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.5414. Min Act: -0.1700

Data Index: 2518907 (Open Web Text)

Max Activating Token Index: 329

Text #18

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.5233. Min Act: -0.1700

Data Index: 4506088 (Open Web Text)

Max Activating Token Index: 849

Text #19

Max Range: 3.9127. Min Range: -3.9127

Max Act: 3.5645. Min Act: -0.1700

Data Index: 4959342 (Open Web Text)

Max Activating Token Index: 752