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

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

Neuron 1196 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: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1118093 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0452. Min Act: -0.0003

Data Index: 651995 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0459. Min Act: -0.0003

Data Index: 822829 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0444. Min Act: -0.0003

Data Index: 20934 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0433. Min Act: -0.0003

Data Index: 751125 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0426. Min Act: -0.0003

Data Index: 448525 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1008592 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0420. Min Act: -0.0003

Data Index: 510170 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0413. Min Act: -0.0003

Data Index: 808303 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0412. Min Act: -0.0003

Data Index: 71582 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0404. Min Act: -0.0003

Data Index: 733401 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0402. Min Act: -0.0003

Data Index: 654175 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0410. Min Act: -0.0003

Data Index: 14070 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0401. Min Act: -0.0002

Data Index: 736752 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0400. Min Act: -0.0003

Data Index: 69527 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0401. Min Act: -0.0003

Data Index: 64764 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0406. Min Act: -0.0003

Data Index: 352385 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1195279 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0407. Min Act: -0.0004

Data Index: 765070 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0404. Min Act: -0.0003

Data Index: 36245 (C4 (Web Text))

Max Activating Token Index: 615