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

Dataset: The Pile

Neuron 1943 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.2253. Min Act: 0.0000

Data Index: 919740 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1073330 (The Pile)

Max Activating Token Index: 789

Text #2

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0161. Min Act: -0.0000

Data Index: 1610481 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0833. Min Act: -0.0000

Data Index: 1152794 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0162. Min Act: -0.0000

Data Index: 1375245 (The Pile)

Max Activating Token Index: 432

Text #5

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0877. Min Act: -0.0000

Data Index: 962405 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0557. Min Act: -0.0000

Data Index: 1685587 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0572. Min Act: -0.0000

Data Index: 364375 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0927. Min Act: -0.0000

Data Index: 1083440 (The Pile)

Max Activating Token Index: 266

Text #9

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1241033 (The Pile)

Max Activating Token Index: 740

Text #10

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0276. Min Act: -0.0000

Data Index: 262345 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0300. Min Act: -0.0000

Data Index: 287783 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0209. Min Act: -0.0000

Data Index: 497113 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1401406 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0085. Min Act: -0.0000

Data Index: 708045 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.9934. Min Act: -0.0000

Data Index: 1172868 (The Pile)

Max Activating Token Index: 61

Text #16

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1950911 (The Pile)

Max Activating Token Index: 373

Text #17

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0019. Min Act: -0.0000

Data Index: 25634 (The Pile)

Max Activating Token Index: 313

Text #18

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.9281. Min Act: -0.0000

Data Index: 667951 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1288853 (The Pile)

Max Activating Token Index: 842