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

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

Neuron 478 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0374. Min Act: -0.0003

Data Index: 467078 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0371. Min Act: -0.0003

Data Index: 378743 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0373. Min Act: -0.0003

Data Index: 770604 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0366. Min Act: -0.0003

Data Index: 207654 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0397. Min Act: -0.0003

Data Index: 678198 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0351. Min Act: -0.0003

Data Index: 160586 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1024480 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0353. Min Act: -0.0003

Data Index: 977584 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0347. Min Act: -0.0003

Data Index: 914398 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0343. Min Act: -0.0003

Data Index: 349387 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0333. Min Act: -0.0003

Data Index: 175536 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0358. Min Act: -0.0003

Data Index: 779596 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1146576 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0347. Min Act: -0.0003

Data Index: 548619 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0338. Min Act: -0.0003

Data Index: 586514 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1046135 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0331. Min Act: -0.0003

Data Index: 389182 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0342. Min Act: -0.0003

Data Index: 90763 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0332. Min Act: -0.0003

Data Index: 262932 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0338. Min Act: -0.0003

Data Index: 497644 (C4 (Web Text))

Max Activating Token Index: 1023