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

Dataset: The Pile

Neuron 2953 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.5079. Min Act: -0.0000

Data Index: 746118 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1940396 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1492362 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1693899 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1041589 (The Pile)

Max Activating Token Index: 959

Text #5

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1389152 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1131441 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4156. Min Act: -0.0000

Data Index: 554418 (The Pile)

Max Activating Token Index: 267

Text #8

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1949618 (The Pile)

Max Activating Token Index: 713

Text #9

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4198. Min Act: -0.0000

Data Index: 426224 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1166910 (The Pile)

Max Activating Token Index: 372

Text #11

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1117972 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1743719 (The Pile)

Max Activating Token Index: 870

Text #13

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4192. Min Act: -0.0000

Data Index: 362571 (The Pile)

Max Activating Token Index: 65

Text #14

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4647. Min Act: -0.0000

Data Index: 354162 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1686920 (The Pile)

Max Activating Token Index: 901

Text #16

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4260. Min Act: -0.0000

Data Index: 614634 (The Pile)

Max Activating Token Index: 670

Text #17

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1212464 (The Pile)

Max Activating Token Index: 218

Text #18

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1110236 (The Pile)

Max Activating Token Index: 330

Text #19

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1917637 (The Pile)

Max Activating Token Index: 985