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

Dataset: Open Web Text

Neuron 1915 in Layer 4

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: 2.2367. Min Range: -2.2367

Max Act: 2.2349. Min Act: -0.1700

Data Index: 6792851 (Open Web Text)

Max Activating Token Index: 971

Text #1

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.2359. Min Act: -0.1700

Data Index: 1218809 (Open Web Text)

Max Activating Token Index: 252

Text #2

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.2367. Min Act: -0.1700

Data Index: 6207769 (Open Web Text)

Max Activating Token Index: 1010

Text #3

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1885. Min Act: -0.1700

Data Index: 7473913 (Open Web Text)

Max Activating Token Index: 668

Text #4

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1587. Min Act: -0.1700

Data Index: 6591396 (Open Web Text)

Max Activating Token Index: 542

Text #5

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1649. Min Act: -0.1700

Data Index: 6619550 (Open Web Text)

Max Activating Token Index: 254

Text #6

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1700. Min Act: -0.1700

Data Index: 182278 (Open Web Text)

Max Activating Token Index: 896

Text #7

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1626. Min Act: -0.1700

Data Index: 6112169 (Open Web Text)

Max Activating Token Index: 272

Text #8

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1827. Min Act: -0.1700

Data Index: 7674315 (Open Web Text)

Max Activating Token Index: 562

Text #9

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1478. Min Act: -0.1700

Data Index: 1962623 (Open Web Text)

Max Activating Token Index: 494

Text #10

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1617. Min Act: -0.1700

Data Index: 6615178 (Open Web Text)

Max Activating Token Index: 274

Text #11

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1620. Min Act: -0.1700

Data Index: 904146 (Open Web Text)

Max Activating Token Index: 781

Text #12

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1331. Min Act: -0.1700

Data Index: 2191661 (Open Web Text)

Max Activating Token Index: 386

Text #13

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1475. Min Act: -0.1700

Data Index: 5124282 (Open Web Text)

Max Activating Token Index: 227

Text #14

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1229. Min Act: -0.1700

Data Index: 3731165 (Open Web Text)

Max Activating Token Index: 403

Text #15

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1180. Min Act: -0.1700

Data Index: 301117 (Open Web Text)

Max Activating Token Index: 906

Text #16

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1392. Min Act: -0.1700

Data Index: 6681650 (Open Web Text)

Max Activating Token Index: 604

Text #17

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1426. Min Act: -0.1700

Data Index: 2416907 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1408. Min Act: -0.1700

Data Index: 5904731 (Open Web Text)

Max Activating Token Index: 304

Text #19

Max Range: 2.2367. Min Range: -2.2367

Max Act: 2.1334. Min Act: -0.1700

Data Index: 204701 (Open Web Text)

Max Activating Token Index: 38