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

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

Neuron 141 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: 0.0449. Min Range: -0.0449

Max Act: 0.0449. Min Act: -0.0004

Data Index: 203567 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0400. Min Act: -0.0003

Data Index: 724612 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0379. Min Act: -0.0003

Data Index: 812668 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0378. Min Act: -0.0003

Data Index: 782580 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0355. Min Act: -0.0004

Data Index: 960675 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0355. Min Act: -0.0003

Data Index: 456804 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0336. Min Act: -0.0003

Data Index: 539207 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0344. Min Act: -0.0003

Data Index: 510393 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0325. Min Act: -0.0003

Data Index: 523773 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0323. Min Act: -0.0003

Data Index: 835059 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0325. Min Act: -0.0003

Data Index: 928882 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0337. Min Act: -0.0003

Data Index: 713860 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0328. Min Act: -0.0004

Data Index: 10806 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0331. Min Act: -0.0003

Data Index: 705165 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0333. Min Act: -0.0003

Data Index: 659518 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0319. Min Act: -0.0003

Data Index: 765739 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1129109 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0325. Min Act: -0.0004

Data Index: 1112431 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1139059 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0308. Min Act: -0.0003

Data Index: 229966 (C4 (Web Text))

Max Activating Token Index: 881