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

Dataset: The Pile

Neuron 1789 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1403350 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1343213 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6833. Min Act: -0.0000

Data Index: 555851 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5842. Min Act: -0.0000

Data Index: 72095 (The Pile)

Max Activating Token Index: 725

Text #4

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5950. Min Act: -0.0000

Data Index: 978102 (The Pile)

Max Activating Token Index: 419

Text #5

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6191. Min Act: -0.0000

Data Index: 55722 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1076142 (The Pile)

Max Activating Token Index: 276

Text #7

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1680097 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5536. Min Act: -0.0000

Data Index: 827037 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5546. Min Act: -0.0000

Data Index: 771798 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5162. Min Act: -0.0000

Data Index: 153066 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5303. Min Act: -0.0000

Data Index: 294595 (The Pile)

Max Activating Token Index: 182

Text #12

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.4971. Min Act: -0.0000

Data Index: 995637 (The Pile)

Max Activating Token Index: 671

Text #13

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.4845. Min Act: -0.0000

Data Index: 945368 (The Pile)

Max Activating Token Index: 701

Text #14

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1619146 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1801063 (The Pile)

Max Activating Token Index: 916

Text #16

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1901045 (The Pile)

Max Activating Token Index: 988

Text #17

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.4392. Min Act: -0.0000

Data Index: 131445 (The Pile)

Max Activating Token Index: 547

Text #18

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.4623. Min Act: -0.0000

Data Index: 129223 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1222785 (The Pile)

Max Activating Token Index: 661