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

Dataset: The Pile

Neuron 3804 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.6228. Min Act: -0.0000

Data Index: 243401 (The Pile)

Max Activating Token Index: 702

Text #1

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5305. Min Act: -0.0000

Data Index: 765747 (The Pile)

Max Activating Token Index: 119

Text #2

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5000. Min Act: -0.0000

Data Index: 457714 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1321920 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5152. Min Act: 0.0000

Data Index: 1181069 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1583011 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1571603 (The Pile)

Max Activating Token Index: 897

Text #7

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1913076 (The Pile)

Max Activating Token Index: 182

Text #8

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4602. Min Act: -0.0000

Data Index: 167309 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4172. Min Act: -0.0000

Data Index: 373888 (The Pile)

Max Activating Token Index: 352

Text #10

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1292946 (The Pile)

Max Activating Token Index: 499

Text #11

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1422047 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1916112 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4184. Min Act: -0.0000

Data Index: 905886 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1451521 (The Pile)

Max Activating Token Index: 926

Text #15

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1725181 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.4054. Min Act: -0.0000

Data Index: 313269 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.3617. Min Act: -0.0000

Data Index: 355543 (The Pile)

Max Activating Token Index: 704

Text #18

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1346884 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.3739. Min Act: -0.0000

Data Index: 15868 (The Pile)

Max Activating Token Index: 231