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

Dataset: Open Web Text

Neuron 942 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: 3.6962. Min Range: -3.6962

Max Act: 3.6962. Min Act: -0.1700

Data Index: 2540645 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.5460. Min Act: -0.1700

Data Index: 7995413 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.5441. Min Act: -0.1700

Data Index: 3944214 (Open Web Text)

Max Activating Token Index: 474

Text #3

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4895. Min Act: -0.1700

Data Index: 5151212 (Open Web Text)

Max Activating Token Index: 784

Text #4

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4767. Min Act: -0.1700

Data Index: 3076736 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4850. Min Act: -0.1700

Data Index: 736480 (Open Web Text)

Max Activating Token Index: 676

Text #6

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4689. Min Act: -0.1700

Data Index: 4836790 (Open Web Text)

Max Activating Token Index: 957

Text #7

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4677. Min Act: -0.1700

Data Index: 5963505 (Open Web Text)

Max Activating Token Index: 603

Text #8

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4725. Min Act: -0.1700

Data Index: 1844963 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4716. Min Act: -0.1700

Data Index: 3717429 (Open Web Text)

Max Activating Token Index: 729

Text #10

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4387. Min Act: -0.1700

Data Index: 5161307 (Open Web Text)

Max Activating Token Index: 45

Text #11

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4283. Min Act: -0.1700

Data Index: 2079200 (Open Web Text)

Max Activating Token Index: 399

Text #12

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4520. Min Act: -0.1700

Data Index: 6727370 (Open Web Text)

Max Activating Token Index: 458

Text #13

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4329. Min Act: -0.1700

Data Index: 6282639 (Open Web Text)

Max Activating Token Index: 233

Text #14

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4510. Min Act: -0.1700

Data Index: 6018495 (Open Web Text)

Max Activating Token Index: 481

Text #15

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4497. Min Act: -0.1700

Data Index: 3036113 (Open Web Text)

Max Activating Token Index: 813

Text #16

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4593. Min Act: -0.1700

Data Index: 1752616 (Open Web Text)

Max Activating Token Index: 360

Text #17

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4369. Min Act: -0.1700

Data Index: 4212402 (Open Web Text)

Max Activating Token Index: 290

Text #18

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4415. Min Act: -0.1700

Data Index: 2774564 (Open Web Text)

Max Activating Token Index: 778

Text #19

Max Range: 3.6962. Min Range: -3.6962

Max Act: 3.4412. Min Act: -0.1700

Data Index: 173015 (Open Web Text)

Max Activating Token Index: 376