Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1104 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0401. Min Act: -0.0004

Data Index: 906810 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0400. Min Act: -0.0004

Data Index: 809878 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0390. Min Act: -0.0004

Data Index: 462332 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0378. Min Act: -0.0004

Data Index: 717788 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0378. Min Act: -0.0004

Data Index: 223788 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0374. Min Act: -0.0004

Data Index: 128130 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0370. Min Act: -0.0004

Data Index: 1026005 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0368. Min Act: -0.0005

Data Index: 111936 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0359. Min Act: -0.0004

Data Index: 978304 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0365. Min Act: -0.0004

Data Index: 375002 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1328988 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0360. Min Act: -0.0004

Data Index: 557610 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0359. Min Act: -0.0004

Data Index: 345361 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0358. Min Act: -0.0004

Data Index: 1175972 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0355. Min Act: -0.0005

Data Index: 771401 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0370. Min Act: -0.0004

Data Index: 510821 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0349. Min Act: -0.0004

Data Index: 1241886 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0354. Min Act: -0.0004

Data Index: 1324314 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0359. Min Act: -0.0004

Data Index: 950688 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0350. Min Act: -0.0004

Data Index: 44500 (C4 (Web Text))

Max Activating Token Index: 567