Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1478 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0372. Min Act: -0.0006

Data Index: 883827 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0364. Min Act: -0.0006

Data Index: 265531 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0341. Min Act: -0.0006

Data Index: 1137119 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0358. Min Act: -0.0006

Data Index: 583906 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0345. Min Act: -0.0006

Data Index: 321199 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0349. Min Act: -0.0006

Data Index: 253452 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0337. Min Act: -0.0006

Data Index: 381563 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0330. Min Act: -0.0006

Data Index: 99362 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0331. Min Act: -0.0006

Data Index: 643652 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0322. Min Act: -0.0006

Data Index: 909563 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0311. Min Act: -0.0006

Data Index: 488484 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0306. Min Act: -0.0006

Data Index: 418811 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0303. Min Act: -0.0006

Data Index: 748386 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0302. Min Act: -0.0006

Data Index: 1182385 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0310. Min Act: -0.0006

Data Index: 407458 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0302. Min Act: -0.0006

Data Index: 14448 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0309. Min Act: -0.0006

Data Index: 506735 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0321. Min Act: -0.0006

Data Index: 1084455 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0304. Min Act: -0.0006

Data Index: 762071 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0292. Min Act: -0.0006

Data Index: 1074258 (C4 (Web Text))

Max Activating Token Index: 697