Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2121 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0444. Min Act: -0.0004

Data Index: 690115 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0434. Min Act: -0.0004

Data Index: 59333 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0369. Min Act: -0.0004

Data Index: 557552 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0368. Min Act: -0.0004

Data Index: 1033611 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0358. Min Act: -0.0004

Data Index: 1029985 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0330. Min Act: -0.0004

Data Index: 962984 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0355. Min Act: -0.0004

Data Index: 78403 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0306. Min Act: -0.0004

Data Index: 1018286 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0331. Min Act: -0.0004

Data Index: 1317570 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0302. Min Act: -0.0004

Data Index: 867365 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0326. Min Act: -0.0004

Data Index: 871345 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0317. Min Act: -0.0004

Data Index: 84392 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0301. Min Act: -0.0004

Data Index: 830246 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0314. Min Act: -0.0004

Data Index: 569566 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0329. Min Act: -0.0004

Data Index: 578147 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0299. Min Act: -0.0004

Data Index: 208608 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1187862 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0312. Min Act: -0.0004

Data Index: 613263 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0309. Min Act: -0.0004

Data Index: 140687 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0301. Min Act: -0.0004

Data Index: 985443 (C4 (Web Text))

Max Activating Token Index: 79