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

Dataset: Open Web Text

Neuron 1866 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: 2.8676. Min Range: -2.8676

Max Act: 2.8676. Min Act: -0.1700

Data Index: 6681917 (Open Web Text)

Max Activating Token Index: 495

Text #1

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.7823. Min Act: -0.1700

Data Index: 3705904 (Open Web Text)

Max Activating Token Index: 665

Text #2

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.8115. Min Act: -0.1700

Data Index: 891462 (Open Web Text)

Max Activating Token Index: 802

Text #3

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.7797. Min Act: -0.1700

Data Index: 876931 (Open Web Text)

Max Activating Token Index: 802

Text #4

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.7442. Min Act: -0.1700

Data Index: 5047829 (Open Web Text)

Max Activating Token Index: 337

Text #5

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.7635. Min Act: -0.1700

Data Index: 5712654 (Open Web Text)

Max Activating Token Index: 452

Text #6

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6920. Min Act: -0.1700

Data Index: 5936758 (Open Web Text)

Max Activating Token Index: 756

Text #7

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6957. Min Act: -0.1700

Data Index: 2154335 (Open Web Text)

Max Activating Token Index: 172

Text #8

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6614. Min Act: -0.1700

Data Index: 4543237 (Open Web Text)

Max Activating Token Index: 136

Text #9

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6610. Min Act: -0.1700

Data Index: 3483869 (Open Web Text)

Max Activating Token Index: 647

Text #10

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6543. Min Act: -0.1700

Data Index: 2216980 (Open Web Text)

Max Activating Token Index: 289

Text #11

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6502. Min Act: -0.1700

Data Index: 1627470 (Open Web Text)

Max Activating Token Index: 915

Text #12

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6513. Min Act: -0.1700

Data Index: 7924045 (Open Web Text)

Max Activating Token Index: 172

Text #13

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6230. Min Act: -0.1700

Data Index: 5354133 (Open Web Text)

Max Activating Token Index: 335

Text #14

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6366. Min Act: -0.1700

Data Index: 3071530 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6394. Min Act: -0.1700

Data Index: 7016478 (Open Web Text)

Max Activating Token Index: 643

Text #16

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6360. Min Act: -0.1700

Data Index: 3770823 (Open Web Text)

Max Activating Token Index: 651

Text #17

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6121. Min Act: -0.1700

Data Index: 4936225 (Open Web Text)

Max Activating Token Index: 690

Text #18

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.5948. Min Act: -0.1700

Data Index: 7058878 (Open Web Text)

Max Activating Token Index: 935

Text #19

Max Range: 2.8676. Min Range: -2.8676

Max Act: 2.6173. Min Act: -0.1700

Data Index: 2098353 (Open Web Text)

Max Activating Token Index: 167