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

Dataset: The Pile

Neuron 3146 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1562363 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2307. Min Act: -0.0000

Data Index: 33423 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1345833 (The Pile)

Max Activating Token Index: 347

Text #3

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1794297 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2612. Min Act: -0.0000

Data Index: 281752 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2428. Min Act: -0.0000

Data Index: 833734 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2462. Min Act: -0.0000

Data Index: 377483 (The Pile)

Max Activating Token Index: 731

Text #7

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2182. Min Act: -0.0000

Data Index: 539362 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2399. Min Act: -0.0000

Data Index: 1951686 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1843069 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1399057 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1579470 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2309. Min Act: -0.0000

Data Index: 800968 (The Pile)

Max Activating Token Index: 296

Text #13

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2301. Min Act: -0.0000

Data Index: 357801 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1390608 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1671902 (The Pile)

Max Activating Token Index: 307

Text #16

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1357125 (The Pile)

Max Activating Token Index: 629

Text #17

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1217194 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1991616 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2177. Min Act: -0.0000

Data Index: 754193 (The Pile)

Max Activating Token Index: 149