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

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

Neuron 3750 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0002

Data Index: 668162 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1340008 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0464. Min Act: -0.0002

Data Index: 550206 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0415. Min Act: -0.0002

Data Index: 689119 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0413. Min Act: -0.0002

Data Index: 813543 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0427. Min Act: -0.0002

Data Index: 863731 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1336218 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1023505 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0405. Min Act: -0.0002

Data Index: 101483 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0398. Min Act: -0.0002

Data Index: 193789 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0388. Min Act: -0.0002

Data Index: 614931 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0402. Min Act: -0.0002

Data Index: 55426 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1445988 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1097656 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0371. Min Act: -0.0002

Data Index: 751776 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0376. Min Act: -0.0002

Data Index: 273881 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0383. Min Act: -0.0002

Data Index: 511111 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1109364 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0358. Min Act: -0.0002

Data Index: 244370 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1166138 (C4 (Web Text))

Max Activating Token Index: 974