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

Dataset: The Pile

Neuron 4683 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.6194. Min Act: -0.0000

Data Index: 788897 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4986. Min Act: -0.0000

Data Index: 896310 (The Pile)

Max Activating Token Index: 437

Text #2

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1318286 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4255. Min Act: -0.0000

Data Index: 273026 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1433587 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4222. Min Act: -0.0000

Data Index: 684982 (The Pile)

Max Activating Token Index: 55

Text #6

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1034951 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4367. Min Act: -0.0000

Data Index: 808561 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4669. Min Act: -0.0000

Data Index: 825580 (The Pile)

Max Activating Token Index: 597

Text #9

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1744144 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1139288 (The Pile)

Max Activating Token Index: 788

Text #11

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1740361 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4213. Min Act: -0.0000

Data Index: 1583679 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4326. Min Act: -0.0000

Data Index: 758002 (The Pile)

Max Activating Token Index: 655

Text #14

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1020124 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1852131 (The Pile)

Max Activating Token Index: 715

Text #16

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1891213 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4160. Min Act: -0.0000

Data Index: 871551 (The Pile)

Max Activating Token Index: 812

Text #18

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1698455 (The Pile)

Max Activating Token Index: 750

Text #19

Max Range: 0.6194. Min Range: -0.6194

Max Act: 0.4132. Min Act: -0.0000

Data Index: 97353 (The Pile)

Max Activating Token Index: 421