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

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

Neuron 4690 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0002

Data Index: 222471 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0293. Min Act: -0.0002

Data Index: 604467 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0297. Min Act: -0.0002

Data Index: 948606 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0290. Min Act: -0.0002

Data Index: 178536 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0291. Min Act: -0.0002

Data Index: 224116 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0291. Min Act: -0.0002

Data Index: 888062 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1186708 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1196659 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0286. Min Act: -0.0002

Data Index: 483429 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0283. Min Act: -0.0002

Data Index: 612624 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0282. Min Act: -0.0002

Data Index: 785039 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1151015 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1040763 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0281. Min Act: -0.0002

Data Index: 220289 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0278. Min Act: -0.0002

Data Index: 331295 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0277. Min Act: -0.0002

Data Index: 240459 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1213784 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0272. Min Act: -0.0002

Data Index: 979534 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0270. Min Act: -0.0002

Data Index: 591484 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0269. Min Act: -0.0002

Data Index: 476261 (C4 (Web Text))

Max Activating Token Index: 192