Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2993 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1279450 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0003

Data Index: 187762 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0399. Min Act: -0.0003

Data Index: 279419 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0448. Min Act: -0.0003

Data Index: 278170 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0343. Min Act: -0.0003

Data Index: 80828 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1325669 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0348. Min Act: -0.0003

Data Index: 1112467 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0430. Min Act: -0.0003

Data Index: 357155 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1056246 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0380. Min Act: -0.0003

Data Index: 508196 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0369. Min Act: -0.0003

Data Index: 679795 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1095991 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0338. Min Act: -0.0003

Data Index: 646542 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0290. Min Act: -0.0003

Data Index: 949235 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0383. Min Act: -0.0003

Data Index: 417287 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0340. Min Act: -0.0003

Data Index: 50512 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0328. Min Act: -0.0003

Data Index: 755092 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0376. Min Act: -0.0002

Data Index: 621364 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0288. Min Act: -0.0002

Data Index: 827712 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0384. Min Act: -0.0003

Data Index: 875881 (C4 (Web Text))

Max Activating Token Index: 147