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

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

Neuron 2047 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0378. Min Act: -0.0006

Data Index: 940789 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0364. Min Act: -0.0006

Data Index: 572644 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0367. Min Act: -0.0006

Data Index: 1040616 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0371. Min Act: -0.0006

Data Index: 1089284 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0362. Min Act: -0.0006

Data Index: 46108 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0358. Min Act: -0.0006

Data Index: 656057 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0349. Min Act: -0.0006

Data Index: 298641 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0345. Min Act: -0.0006

Data Index: 474756 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0343. Min Act: -0.0006

Data Index: 791773 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0340. Min Act: -0.0006

Data Index: 384960 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0336. Min Act: -0.0006

Data Index: 1310509 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0336. Min Act: -0.0006

Data Index: 1240927 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0333. Min Act: -0.0006

Data Index: 331318 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0333. Min Act: -0.0006

Data Index: 586950 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0325. Min Act: -0.0006

Data Index: 1352259 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0311. Min Act: -0.0006

Data Index: 11793 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0321. Min Act: -0.0006

Data Index: 515612 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0321. Min Act: -0.0006

Data Index: 483447 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0320. Min Act: -0.0006

Data Index: 553826 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0319. Min Act: -0.0006

Data Index: 379339 (C4 (Web Text))

Max Activating Token Index: 344