Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 822 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0291. Min Act: -0.0006

Data Index: 728545 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0294. Min Act: -0.0006

Data Index: 181024 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1106457 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0265. Min Act: -0.0006

Data Index: 545528 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0255. Min Act: -0.0006

Data Index: 524205 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0262. Min Act: -0.0006

Data Index: 91396 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0255. Min Act: -0.0006

Data Index: 18776 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0254. Min Act: -0.0006

Data Index: 940769 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0242. Min Act: -0.0006

Data Index: 742292 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0241. Min Act: -0.0006

Data Index: 482769 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1335417 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0243. Min Act: -0.0006

Data Index: 885956 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0237. Min Act: -0.0006

Data Index: 763633 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0232. Min Act: -0.0006

Data Index: 263267 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0238. Min Act: -0.0006

Data Index: 2368 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0223. Min Act: -0.0006

Data Index: 834818 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0237. Min Act: -0.0006

Data Index: 563874 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0236. Min Act: -0.0006

Data Index: 258354 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1056206 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1266949 (C4 (Web Text))

Max Activating Token Index: 945