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

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

Neuron 220 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0006

Data Index: 1060627 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0273. Min Act: -0.0006

Data Index: 349965 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0269. Min Act: -0.0006

Data Index: 8781 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0268. Min Act: -0.0006

Data Index: 389581 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0264. Min Act: -0.0006

Data Index: 727971 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0269. Min Act: -0.0006

Data Index: 1228980 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0259. Min Act: -0.0006

Data Index: 248792 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0250. Min Act: -0.0006

Data Index: 366326 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0249. Min Act: -0.0005

Data Index: 1187121 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0248. Min Act: -0.0006

Data Index: 210151 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0243. Min Act: -0.0006

Data Index: 590478 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0243. Min Act: -0.0006

Data Index: 687930 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0241. Min Act: -0.0006

Data Index: 130776 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0238. Min Act: -0.0006

Data Index: 524459 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0231. Min Act: -0.0006

Data Index: 958578 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0231. Min Act: -0.0006

Data Index: 754495 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0229. Min Act: -0.0006

Data Index: 13020 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0234. Min Act: -0.0006

Data Index: 693986 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0233. Min Act: -0.0006

Data Index: 469225 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1297164 (C4 (Web Text))

Max Activating Token Index: 1014