Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4041 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3294. Min Act: -0.0001

Data Index: 1359206 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2694. Min Act: -0.0000

Data Index: 59260 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2587. Min Act: -0.0000

Data Index: 281334 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2582. Min Act: -0.0000

Data Index: 476685 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2414. Min Act: -0.0000

Data Index: 177260 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2535. Min Act: -0.0000

Data Index: 620424 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2592. Min Act: -0.0000

Data Index: 94888 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2346. Min Act: -0.0000

Data Index: 11746 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2369. Min Act: -0.0000

Data Index: 497591 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2307. Min Act: -0.0001

Data Index: 943411 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2495. Min Act: -0.0001

Data Index: 220179 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2327. Min Act: -0.0001

Data Index: 783966 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2229. Min Act: -0.0001

Data Index: 840099 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2184. Min Act: -0.0000

Data Index: 12467 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2269. Min Act: -0.0000

Data Index: 79801 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2349. Min Act: -0.0001

Data Index: 1302106 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2270. Min Act: -0.0001

Data Index: 980845 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2243. Min Act: -0.0000

Data Index: 771526 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2080. Min Act: -0.0000

Data Index: 1137991 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2474. Min Act: -0.0001

Data Index: 1239492 (C4 (Web Text))

Max Activating Token Index: 818