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

Dataset: Open Web Text

Neuron 94 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: 5.4354. Min Range: -5.4354

Max Act: 5.4354. Min Act: -0.1700

Data Index: 5171132 (Open Web Text)

Max Activating Token Index: 324

Text #1

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.8625. Min Act: -0.1700

Data Index: 677808 (Open Web Text)

Max Activating Token Index: 516

Text #2

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.7606. Min Act: -0.1700

Data Index: 7711737 (Open Web Text)

Max Activating Token Index: 1006

Text #3

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.7149. Min Act: -0.1700

Data Index: 7264090 (Open Web Text)

Max Activating Token Index: 473

Text #4

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.6860. Min Act: -0.1700

Data Index: 8187337 (Open Web Text)

Max Activating Token Index: 314

Text #5

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.6445. Min Act: -0.1700

Data Index: 3821535 (Open Web Text)

Max Activating Token Index: 91

Text #6

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.6337. Min Act: -0.1700

Data Index: 2739101 (Open Web Text)

Max Activating Token Index: 231

Text #7

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.6482. Min Act: -0.1700

Data Index: 3344067 (Open Web Text)

Max Activating Token Index: 425

Text #8

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.6384. Min Act: -0.1700

Data Index: 8613865 (Open Web Text)

Max Activating Token Index: 710

Text #9

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.6080. Min Act: -0.1700

Data Index: 3238509 (Open Web Text)

Max Activating Token Index: 961

Text #10

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.6455. Min Act: -0.1700

Data Index: 2081188 (Open Web Text)

Max Activating Token Index: 556

Text #11

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.6327. Min Act: -0.1700

Data Index: 476857 (Open Web Text)

Max Activating Token Index: 855

Text #12

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.5460. Min Act: -0.1700

Data Index: 8493724 (Open Web Text)

Max Activating Token Index: 891

Text #13

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.5992. Min Act: -0.1700

Data Index: 6583414 (Open Web Text)

Max Activating Token Index: 946

Text #14

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.5915. Min Act: -0.1700

Data Index: 5574759 (Open Web Text)

Max Activating Token Index: 759

Text #15

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.6135. Min Act: -0.1700

Data Index: 1434224 (Open Web Text)

Max Activating Token Index: 511

Text #16

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.5632. Min Act: -0.1700

Data Index: 2282054 (Open Web Text)

Max Activating Token Index: 31

Text #17

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.5318. Min Act: -0.1700

Data Index: 6640969 (Open Web Text)

Max Activating Token Index: 419

Text #18

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.5275. Min Act: -0.1700

Data Index: 4812446 (Open Web Text)

Max Activating Token Index: 448

Text #19

Max Range: 5.4354. Min Range: -5.4354

Max Act: 4.5055. Min Act: -0.1700

Data Index: 4566909 (Open Web Text)

Max Activating Token Index: 906