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

Dataset: Open Web Text

Neuron 427 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: 3.7459. Min Range: -3.7459

Max Act: 3.6850. Min Act: -0.1700

Data Index: 6030145 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.7459. Min Act: -0.1700

Data Index: 2290086 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.7142. Min Act: -0.1700

Data Index: 1091366 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.7116. Min Act: -0.1700

Data Index: 4557768 (Open Web Text)

Max Activating Token Index: 53

Text #4

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.6397. Min Act: -0.1700

Data Index: 3085203 (Open Web Text)

Max Activating Token Index: 629

Text #5

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.6286. Min Act: -0.1700

Data Index: 3472906 (Open Web Text)

Max Activating Token Index: 372

Text #6

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.7052. Min Act: -0.1700

Data Index: 4188637 (Open Web Text)

Max Activating Token Index: 359

Text #7

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.6391. Min Act: -0.1700

Data Index: 8153964 (Open Web Text)

Max Activating Token Index: 102

Text #8

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.6758. Min Act: -0.1700

Data Index: 6366621 (Open Web Text)

Max Activating Token Index: 855

Text #9

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.6434. Min Act: -0.1700

Data Index: 4668366 (Open Web Text)

Max Activating Token Index: 166

Text #10

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.5808. Min Act: -0.1700

Data Index: 1543068 (Open Web Text)

Max Activating Token Index: 588

Text #11

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.6559. Min Act: -0.1700

Data Index: 5737783 (Open Web Text)

Max Activating Token Index: 864

Text #12

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.5722. Min Act: -0.1700

Data Index: 3029929 (Open Web Text)

Max Activating Token Index: 89

Text #13

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.6063. Min Act: -0.1700

Data Index: 8045005 (Open Web Text)

Max Activating Token Index: 791

Text #14

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.6124. Min Act: -0.1700

Data Index: 7698333 (Open Web Text)

Max Activating Token Index: 631

Text #15

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.6450. Min Act: -0.1700

Data Index: 6697359 (Open Web Text)

Max Activating Token Index: 467

Text #16

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.5951. Min Act: -0.1700

Data Index: 2329614 (Open Web Text)

Max Activating Token Index: 244

Text #17

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.5309. Min Act: -0.1700

Data Index: 6028553 (Open Web Text)

Max Activating Token Index: 519

Text #18

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.5619. Min Act: -0.1700

Data Index: 5325593 (Open Web Text)

Max Activating Token Index: 588

Text #19

Max Range: 3.7459. Min Range: -3.7459

Max Act: 3.5497. Min Act: -0.1700

Data Index: 5848656 (Open Web Text)

Max Activating Token Index: 500