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

Dataset: Open Web Text

Neuron 1667 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: 6.4358. Min Range: -6.4358

Max Act: 6.4358. Min Act: -0.1700

Data Index: 5983723 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 6.4358. Min Range: -6.4358

Max Act: 5.5406. Min Act: -0.1700

Data Index: 482445 (Open Web Text)

Max Activating Token Index: 769

Text #2

Max Range: 6.4358. Min Range: -6.4358

Max Act: 5.4462. Min Act: -0.1700

Data Index: 5904716 (Open Web Text)

Max Activating Token Index: 899

Text #3

Max Range: 6.4358. Min Range: -6.4358

Max Act: 5.3141. Min Act: -0.1700

Data Index: 3663871 (Open Web Text)

Max Activating Token Index: 962

Text #4

Max Range: 6.4358. Min Range: -6.4358

Max Act: 5.3173. Min Act: -0.1700

Data Index: 1104763 (Open Web Text)

Max Activating Token Index: 931

Text #5

Max Range: 6.4358. Min Range: -6.4358

Max Act: 5.2333. Min Act: -0.1700

Data Index: 1262918 (Open Web Text)

Max Activating Token Index: 733

Text #6

Max Range: 6.4358. Min Range: -6.4358

Max Act: 5.1850. Min Act: -0.1700

Data Index: 7160980 (Open Web Text)

Max Activating Token Index: 763

Text #7

Max Range: 6.4358. Min Range: -6.4358

Max Act: 5.1609. Min Act: -0.1700

Data Index: 590055 (Open Web Text)

Max Activating Token Index: 471

Text #8

Max Range: 6.4358. Min Range: -6.4358

Max Act: 5.1326. Min Act: -0.1700

Data Index: 8729048 (Open Web Text)

Max Activating Token Index: 107

Text #9

Max Range: 6.4358. Min Range: -6.4358

Max Act: 5.0773. Min Act: -0.1700

Data Index: 3448743 (Open Web Text)

Max Activating Token Index: 669

Text #10

Max Range: 6.4358. Min Range: -6.4358

Max Act: 5.0823. Min Act: -0.1700

Data Index: 162023 (Open Web Text)

Max Activating Token Index: 353

Text #11

Max Range: 6.4358. Min Range: -6.4358

Max Act: 5.0104. Min Act: -0.1700

Data Index: 3716124 (Open Web Text)

Max Activating Token Index: 992

Text #12

Max Range: 6.4358. Min Range: -6.4358

Max Act: 4.9919. Min Act: -0.1700

Data Index: 1439358 (Open Web Text)

Max Activating Token Index: 519

Text #13

Max Range: 6.4358. Min Range: -6.4358

Max Act: 4.9933. Min Act: -0.1700

Data Index: 7224840 (Open Web Text)

Max Activating Token Index: 718

Text #14

Max Range: 6.4358. Min Range: -6.4358

Max Act: 4.9482. Min Act: -0.1700

Data Index: 2356298 (Open Web Text)

Max Activating Token Index: 906

Text #15

Max Range: 6.4358. Min Range: -6.4358

Max Act: 4.9366. Min Act: -0.1700

Data Index: 7517478 (Open Web Text)

Max Activating Token Index: 846

Text #16

Max Range: 6.4358. Min Range: -6.4358

Max Act: 4.9398. Min Act: -0.1700

Data Index: 1085619 (Open Web Text)

Max Activating Token Index: 414

Text #17

Max Range: 6.4358. Min Range: -6.4358

Max Act: 4.9726. Min Act: -0.1700

Data Index: 6450029 (Open Web Text)

Max Activating Token Index: 194

Text #18

Max Range: 6.4358. Min Range: -6.4358

Max Act: 4.9581. Min Act: -0.1700

Data Index: 3090045 (Open Web Text)

Max Activating Token Index: 82

Text #19

Max Range: 6.4358. Min Range: -6.4358

Max Act: 4.9191. Min Act: -0.1700

Data Index: 507319 (Open Web Text)

Max Activating Token Index: 31