Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 882 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0004

Data Index: 199700 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0436. Min Act: -0.0004

Data Index: 269363 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0389. Min Act: -0.0004

Data Index: 1343344 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0378. Min Act: -0.0005

Data Index: 219470 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0356. Min Act: -0.0005

Data Index: 504226 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0355. Min Act: -0.0004

Data Index: 156659 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0336. Min Act: -0.0004

Data Index: 1192035 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0328. Min Act: -0.0004

Data Index: 777476 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0317. Min Act: -0.0004

Data Index: 959212 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0316. Min Act: -0.0004

Data Index: 92525 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0314. Min Act: -0.0004

Data Index: 707836 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0311. Min Act: -0.0004

Data Index: 728385 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0310. Min Act: -0.0004

Data Index: 314035 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0309. Min Act: -0.0005

Data Index: 795429 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0309. Min Act: -0.0004

Data Index: 261639 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0307. Min Act: -0.0005

Data Index: 513503 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0308. Min Act: -0.0004

Data Index: 1021983 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0306. Min Act: -0.0004

Data Index: 1235225 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0298. Min Act: -0.0004

Data Index: 236670 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0298. Min Act: -0.0004

Data Index: 573008 (C4 (Web Text))

Max Activating Token Index: 938