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

Dataset: Open Web Text

Neuron 2799 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: 5.1365. Min Range: -5.1365

Max Act: 5.1365. Min Act: -0.1700

Data Index: 721188 (Open Web Text)

Max Activating Token Index: 161

Text #1

Max Range: 5.1365. Min Range: -5.1365

Max Act: 5.0708. Min Act: -0.1700

Data Index: 6978811 (Open Web Text)

Max Activating Token Index: 210

Text #2

Max Range: 5.1365. Min Range: -5.1365

Max Act: 5.0467. Min Act: -0.1700

Data Index: 4656797 (Open Web Text)

Max Activating Token Index: 728

Text #3

Max Range: 5.1365. Min Range: -5.1365

Max Act: 5.0046. Min Act: -0.1700

Data Index: 1407910 (Open Web Text)

Max Activating Token Index: 1004

Text #4

Max Range: 5.1365. Min Range: -5.1365

Max Act: 5.0232. Min Act: -0.1700

Data Index: 5366052 (Open Web Text)

Max Activating Token Index: 743

Text #5

Max Range: 5.1365. Min Range: -5.1365

Max Act: 5.0015. Min Act: -0.1700

Data Index: 5218610 (Open Web Text)

Max Activating Token Index: 251

Text #6

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9576. Min Act: -0.1700

Data Index: 172721 (Open Web Text)

Max Activating Token Index: 667

Text #7

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9374. Min Act: -0.1700

Data Index: 7586725 (Open Web Text)

Max Activating Token Index: 723

Text #8

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9720. Min Act: -0.1700

Data Index: 1020988 (Open Web Text)

Max Activating Token Index: 907

Text #9

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9792. Min Act: -0.1700

Data Index: 6530470 (Open Web Text)

Max Activating Token Index: 951

Text #10

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9418. Min Act: -0.1700

Data Index: 4035515 (Open Web Text)

Max Activating Token Index: 947

Text #11

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9274. Min Act: -0.1700

Data Index: 4378074 (Open Web Text)

Max Activating Token Index: 875

Text #12

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.8739. Min Act: -0.1700

Data Index: 1200255 (Open Web Text)

Max Activating Token Index: 372

Text #13

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.8639. Min Act: -0.1700

Data Index: 7199287 (Open Web Text)

Max Activating Token Index: 403

Text #14

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.9055. Min Act: -0.1700

Data Index: 3674430 (Open Web Text)

Max Activating Token Index: 313

Text #15

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.8440. Min Act: -0.1700

Data Index: 7630884 (Open Web Text)

Max Activating Token Index: 285

Text #16

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.8583. Min Act: -0.1700

Data Index: 2265391 (Open Web Text)

Max Activating Token Index: 210

Text #17

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.7743. Min Act: -0.1700

Data Index: 3594087 (Open Web Text)

Max Activating Token Index: 666

Text #18

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.8700. Min Act: -0.1700

Data Index: 1970904 (Open Web Text)

Max Activating Token Index: 756

Text #19

Max Range: 5.1365. Min Range: -5.1365

Max Act: 4.8326. Min Act: -0.1700

Data Index: 1176767 (Open Web Text)

Max Activating Token Index: 112