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

Dataset: Open Web Text

Neuron 412 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: 2.0038. Min Range: -2.0038

Max Act: 2.0038. Min Act: -0.1700

Data Index: 1454659 (Open Web Text)

Max Activating Token Index: 829

Text #1

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9982. Min Act: -0.1700

Data Index: 2516022 (Open Web Text)

Max Activating Token Index: 652

Text #2

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9800. Min Act: -0.1700

Data Index: 6163905 (Open Web Text)

Max Activating Token Index: 714

Text #3

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9833. Min Act: -0.1700

Data Index: 6231801 (Open Web Text)

Max Activating Token Index: 194

Text #4

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9702. Min Act: -0.1700

Data Index: 7324802 (Open Web Text)

Max Activating Token Index: 121

Text #5

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9713. Min Act: -0.1700

Data Index: 2384299 (Open Web Text)

Max Activating Token Index: 150

Text #6

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9733. Min Act: -0.1700

Data Index: 450956 (Open Web Text)

Max Activating Token Index: 687

Text #7

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9515. Min Act: -0.1700

Data Index: 8808289 (Open Web Text)

Max Activating Token Index: 608

Text #8

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9522. Min Act: -0.1700

Data Index: 4076425 (Open Web Text)

Max Activating Token Index: 563

Text #9

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9573. Min Act: -0.1700

Data Index: 8037438 (Open Web Text)

Max Activating Token Index: 721

Text #10

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9428. Min Act: -0.1700

Data Index: 6324040 (Open Web Text)

Max Activating Token Index: 616

Text #11

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9351. Min Act: -0.1700

Data Index: 5964562 (Open Web Text)

Max Activating Token Index: 624

Text #12

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9146. Min Act: -0.1700

Data Index: 5394802 (Open Web Text)

Max Activating Token Index: 637

Text #13

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9352. Min Act: -0.1700

Data Index: 1883409 (Open Web Text)

Max Activating Token Index: 735

Text #14

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9421. Min Act: -0.1700

Data Index: 1827873 (Open Web Text)

Max Activating Token Index: 700

Text #15

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9347. Min Act: -0.1700

Data Index: 8585370 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9325. Min Act: -0.1700

Data Index: 511869 (Open Web Text)

Max Activating Token Index: 494

Text #17

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9419. Min Act: -0.1700

Data Index: 1782691 (Open Web Text)

Max Activating Token Index: 739

Text #18

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9140. Min Act: -0.1700

Data Index: 507315 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.9078. Min Act: -0.1700

Data Index: 5562771 (Open Web Text)

Max Activating Token Index: 191