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

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

Neuron 2656 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1184134 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0254. Min Act: -0.0002

Data Index: 60094 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0258. Min Act: -0.0001

Data Index: 216134 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0281. Min Act: -0.0001

Data Index: 581560 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0312. Min Act: -0.0002

Data Index: 716678 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0277. Min Act: -0.0001

Data Index: 19986 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0260. Min Act: -0.0002

Data Index: 398597 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0215. Min Act: -0.0002

Data Index: 261459 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0274. Min Act: -0.0001

Data Index: 602273 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0224. Min Act: -0.0001

Data Index: 195915 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0239. Min Act: -0.0002

Data Index: 728613 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0218. Min Act: -0.0002

Data Index: 822549 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1238753 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0235. Min Act: -0.0001

Data Index: 945476 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0253. Min Act: -0.0002

Data Index: 347495 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0266. Min Act: -0.0001

Data Index: 185002 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0292. Min Act: -0.0002

Data Index: 989519 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0278. Min Act: -0.0002

Data Index: 351202 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0281. Min Act: -0.0002

Data Index: 445219 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0250. Min Act: -0.0001

Data Index: 714744 (C4 (Web Text))

Max Activating Token Index: 1010