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

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

Neuron 85 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2319. Min Act: -0.0000

Data Index: 828936 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1259627 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1159262 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1222664 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2305. Min Act: -0.0000

Data Index: 25335 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2374. Min Act: -0.0001

Data Index: 1254129 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1033589 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2350. Min Act: -0.0000

Data Index: 761235 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2254. Min Act: -0.0000

Data Index: 942494 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1113401 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2243. Min Act: 0.0000

Data Index: 413784 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2216. Min Act: -0.0000

Data Index: 988722 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2227. Min Act: -0.0000

Data Index: 8621 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2159. Min Act: -0.0000

Data Index: 338155 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2138. Min Act: -0.0000

Data Index: 998874 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2193. Min Act: -0.0000

Data Index: 891956 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2253. Min Act: -0.0000

Data Index: 808192 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2184. Min Act: -0.0000

Data Index: 196933 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2045. Min Act: -0.0000

Data Index: 292614 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1003063 (C4 (Web Text))

Max Activating Token Index: 422