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

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

Neuron 169 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: 0.0490. Min Range: -0.0490

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1326804 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1054200 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0443. Min Act: -0.0003

Data Index: 219675 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1094965 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0450. Min Act: -0.0003

Data Index: 310030 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0397. Min Act: -0.0003

Data Index: 149062 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0386. Min Act: -0.0003

Data Index: 732306 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0391. Min Act: -0.0003

Data Index: 30819 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1571022 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0382. Min Act: -0.0003

Data Index: 32833 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0354. Min Act: -0.0003

Data Index: 640263 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1209083 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0377. Min Act: -0.0003

Data Index: 386235 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0361. Min Act: -0.0003

Data Index: 476266 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0372. Min Act: -0.0003

Data Index: 921797 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0378. Min Act: -0.0003

Data Index: 898048 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0368. Min Act: -0.0003

Data Index: 548842 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0347. Min Act: -0.0003

Data Index: 519625 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1477240 (Python Code)

Max Activating Token Index: 712

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1139677 (C4 (Web Text))

Max Activating Token Index: 501