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

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

Neuron 3242 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0001

Data Index: 676787 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1085059 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1226089 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0258. Min Act: -0.0001

Data Index: 296219 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1235437 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0237. Min Act: -0.0001

Data Index: 842759 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0221. Min Act: -0.0001

Data Index: 730410 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0219. Min Act: -0.0001

Data Index: 1187578 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0246. Min Act: -0.0001

Data Index: 499287 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0211. Min Act: -0.0001

Data Index: 246795 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1355972 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0208. Min Act: -0.0001

Data Index: 284181 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0208. Min Act: -0.0001

Data Index: 306638 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1581069 (Python Code)

Max Activating Token Index: 341

Text #14

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1233894 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0213. Min Act: -0.0001

Data Index: 643967 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0209. Min Act: -0.0001

Data Index: 513532 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0221. Min Act: -0.0001

Data Index: 271333 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0214. Min Act: -0.0001

Data Index: 985948 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0214. Min Act: -0.0001

Data Index: 96266 (C4 (Web Text))

Max Activating Token Index: 664