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

Dataset: Open Web Text

Neuron 1716 in Layer 5

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: 3.9454. Min Range: -3.9454

Max Act: 3.9454. Min Act: -0.1700

Data Index: 1725162 (Open Web Text)

Max Activating Token Index: 798

Text #1

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.6431. Min Act: -0.1700

Data Index: 1415165 (Open Web Text)

Max Activating Token Index: 727

Text #2

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.6232. Min Act: -0.1700

Data Index: 2972831 (Open Web Text)

Max Activating Token Index: 387

Text #3

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.6100. Min Act: -0.1700

Data Index: 2430263 (Open Web Text)

Max Activating Token Index: 951

Text #4

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.6281. Min Act: -0.1700

Data Index: 4710654 (Open Web Text)

Max Activating Token Index: 811

Text #5

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.5714. Min Act: -0.1700

Data Index: 6320722 (Open Web Text)

Max Activating Token Index: 151

Text #6

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.5358. Min Act: -0.1700

Data Index: 1466811 (Open Web Text)

Max Activating Token Index: 586

Text #7

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.5269. Min Act: -0.1700

Data Index: 3581547 (Open Web Text)

Max Activating Token Index: 207

Text #8

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.5460. Min Act: -0.1700

Data Index: 132448 (Open Web Text)

Max Activating Token Index: 597

Text #9

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.5343. Min Act: -0.1700

Data Index: 741485 (Open Web Text)

Max Activating Token Index: 787

Text #10

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.5093. Min Act: -0.1700

Data Index: 2637902 (Open Web Text)

Max Activating Token Index: 522

Text #11

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.5047. Min Act: -0.1700

Data Index: 2061515 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.4735. Min Act: -0.1700

Data Index: 1985054 (Open Web Text)

Max Activating Token Index: 996

Text #13

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.4662. Min Act: -0.1700

Data Index: 7542348 (Open Web Text)

Max Activating Token Index: 248

Text #14

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.4646. Min Act: -0.1700

Data Index: 4260990 (Open Web Text)

Max Activating Token Index: 842

Text #15

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.4564. Min Act: -0.1700

Data Index: 2458738 (Open Web Text)

Max Activating Token Index: 915

Text #16

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.4326. Min Act: -0.1700

Data Index: 595444 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.4421. Min Act: -0.1700

Data Index: 7728464 (Open Web Text)

Max Activating Token Index: 120

Text #18

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.4160. Min Act: -0.1700

Data Index: 4147602 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 3.9454. Min Range: -3.9454

Max Act: 3.4513. Min Act: -0.1700

Data Index: 6732774 (Open Web Text)

Max Activating Token Index: 943