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

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

Neuron 577 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2995. Min Act: -0.0001

Data Index: 177946 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2668. Min Act: -0.0001

Data Index: 251950 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2698. Min Act: -0.0001

Data Index: 746257 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2490. Min Act: -0.0001

Data Index: 1206190 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2227. Min Act: -0.0001

Data Index: 742296 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2065. Min Act: -0.0001

Data Index: 213852 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2299. Min Act: -0.0001

Data Index: 1233190 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2271. Min Act: -0.0001

Data Index: 591 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2221. Min Act: -0.0001

Data Index: 911831 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2172. Min Act: -0.0001

Data Index: 391833 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2023. Min Act: -0.0001

Data Index: 399295 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2178. Min Act: -0.0001

Data Index: 676236 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2002. Min Act: -0.0001

Data Index: 1110941 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2148. Min Act: -0.0001

Data Index: 1297403 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2219. Min Act: -0.0001

Data Index: 110197 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2129. Min Act: -0.0001

Data Index: 352792 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2066. Min Act: -0.0001

Data Index: 1173035 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2060. Min Act: -0.0001

Data Index: 53471 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2156. Min Act: -0.0001

Data Index: 361083 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2282. Min Act: -0.0001

Data Index: 737278 (C4 (Web Text))

Max Activating Token Index: 720