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

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

Neuron 163 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: 0.0461. Min Range: -0.0461

Max Act: 0.0461. Min Act: -0.0004

Data Index: 38673 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0448. Min Act: -0.0004

Data Index: 1238761 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0452. Min Act: -0.0003

Data Index: 912869 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1325737 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0426. Min Act: -0.0004

Data Index: 102375 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0428. Min Act: -0.0004

Data Index: 1286284 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0417. Min Act: -0.0003

Data Index: 822291 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0418. Min Act: -0.0004

Data Index: 150556 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0432. Min Act: -0.0004

Data Index: 1109497 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0439. Min Act: -0.0003

Data Index: 522635 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1321294 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1252514 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1108366 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0393. Min Act: -0.0004

Data Index: 30964 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0404. Min Act: -0.0002

Data Index: 888593 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0395. Min Act: -0.0003

Data Index: 262360 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0389. Min Act: -0.0003

Data Index: 836848 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0383. Min Act: -0.0003

Data Index: 95952 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0387. Min Act: -0.0004

Data Index: 622827 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0400. Min Act: -0.0003

Data Index: 34962 (C4 (Web Text))

Max Activating Token Index: 195