Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4603 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.5226. Min Act: -0.0003

Data Index: 865806 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4381. Min Act: -0.0003

Data Index: 869882 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4196. Min Act: -0.0002

Data Index: 1149300 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4355. Min Act: -0.0003

Data Index: 647052 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4102. Min Act: -0.0003

Data Index: 1136064 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4022. Min Act: -0.0003

Data Index: 1054685 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3855. Min Act: -0.0003

Data Index: 882421 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4009. Min Act: -0.0003

Data Index: 1030990 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3740. Min Act: -0.0003

Data Index: 710173 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3631. Min Act: -0.0003

Data Index: 784357 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3938. Min Act: -0.0002

Data Index: 637095 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3595. Min Act: -0.0003

Data Index: 640257 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3554. Min Act: -0.0003

Data Index: 399369 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3528. Min Act: -0.0003

Data Index: 14091 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3529. Min Act: -0.0003

Data Index: 987299 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3378. Min Act: -0.0002

Data Index: 703551 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3586. Min Act: -0.0003

Data Index: 516535 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3365. Min Act: -0.0002

Data Index: 933310 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3235. Min Act: -0.0003

Data Index: 1174537 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3319. Min Act: -0.0003

Data Index: 170157 (C4 (Web Text))

Max Activating Token Index: 10