Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2783 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1271547 (The Pile)

Max Activating Token Index: 872

Text #1

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2932. Min Act: -0.0000

Data Index: 172767 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1899089 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1126348 (The Pile)

Max Activating Token Index: 189

Text #4

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2565. Min Act: -0.0000

Data Index: 503475 (The Pile)

Max Activating Token Index: 209

Text #5

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1909174 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2556. Min Act: -0.0000

Data Index: 40237 (The Pile)

Max Activating Token Index: 61

Text #7

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2531. Min Act: -0.0000

Data Index: 445825 (The Pile)

Max Activating Token Index: 905

Text #8

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1029934 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2235. Min Act: -0.0000

Data Index: 718365 (The Pile)

Max Activating Token Index: 211

Text #10

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1371258 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1405901 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1983554 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1203477 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1357356 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1023174 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2225. Min Act: -0.0000

Data Index: 605368 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2263. Min Act: -0.0000

Data Index: 805661 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1030897 (The Pile)

Max Activating Token Index: 647

Text #19

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1684715 (The Pile)

Max Activating Token Index: 738