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

Dataset: Open Web Text

Neuron 31 in Layer 2

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: 3.1438. Min Range: -3.1438

Max Act: 3.1438. Min Act: -0.1700

Data Index: 7953689 (Open Web Text)

Max Activating Token Index: 253

Text #1

Max Range: 3.1438. Min Range: -3.1438

Max Act: 3.0909. Min Act: -0.1700

Data Index: 7204963 (Open Web Text)

Max Activating Token Index: 722

Text #2

Max Range: 3.1438. Min Range: -3.1438

Max Act: 3.0420. Min Act: -0.1700

Data Index: 7344825 (Open Web Text)

Max Activating Token Index: 737

Text #3

Max Range: 3.1438. Min Range: -3.1438

Max Act: 3.0172. Min Act: -0.1700

Data Index: 764982 (Open Web Text)

Max Activating Token Index: 409

Text #4

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9931. Min Act: -0.1700

Data Index: 4622668 (Open Web Text)

Max Activating Token Index: 486

Text #5

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9685. Min Act: -0.1700

Data Index: 8504557 (Open Web Text)

Max Activating Token Index: 541

Text #6

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9913. Min Act: -0.1700

Data Index: 1519331 (Open Web Text)

Max Activating Token Index: 656

Text #7

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9718. Min Act: -0.1700

Data Index: 3464882 (Open Web Text)

Max Activating Token Index: 481

Text #8

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9695. Min Act: -0.1700

Data Index: 2724345 (Open Web Text)

Max Activating Token Index: 408

Text #9

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9755. Min Act: -0.1700

Data Index: 2108996 (Open Web Text)

Max Activating Token Index: 1000

Text #10

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9583. Min Act: -0.1700

Data Index: 3793062 (Open Web Text)

Max Activating Token Index: 295

Text #11

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9503. Min Act: -0.1700

Data Index: 6420238 (Open Web Text)

Max Activating Token Index: 895

Text #12

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9466. Min Act: -0.1700

Data Index: 7390035 (Open Web Text)

Max Activating Token Index: 605

Text #13

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9399. Min Act: -0.1700

Data Index: 6487114 (Open Web Text)

Max Activating Token Index: 962

Text #14

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9755. Min Act: -0.1700

Data Index: 2985865 (Open Web Text)

Max Activating Token Index: 981

Text #15

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9397. Min Act: -0.1700

Data Index: 4949570 (Open Web Text)

Max Activating Token Index: 186

Text #16

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9425. Min Act: -0.1700

Data Index: 3802967 (Open Web Text)

Max Activating Token Index: 987

Text #17

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9496. Min Act: -0.1700

Data Index: 6940134 (Open Web Text)

Max Activating Token Index: 52

Text #18

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9376. Min Act: -0.1700

Data Index: 1323902 (Open Web Text)

Max Activating Token Index: 80

Text #19

Max Range: 3.1438. Min Range: -3.1438

Max Act: 2.9331. Min Act: -0.1700

Data Index: 3167750 (Open Web Text)

Max Activating Token Index: 185