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

Dataset: The Pile

Neuron 4675 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: 0.5357. Min Range: -0.5357

Max Act: 0.5357. Min Act: 0.0000

Data Index: 25527 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4652. Min Act: 0.0000

Data Index: 737183 (The Pile)

Max Activating Token Index: 866

Text #2

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.5007. Min Act: -0.0000

Data Index: 571756 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1519565 (The Pile)

Max Activating Token Index: 160

Text #4

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1375980 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4523. Min Act: 0.0000

Data Index: 1925395 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1803093 (The Pile)

Max Activating Token Index: 305

Text #7

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3900. Min Act: -0.0000

Data Index: 585288 (The Pile)

Max Activating Token Index: 698

Text #8

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1249741 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3254. Min Act: -0.0000

Data Index: 160213 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3862. Min Act: 0.0000

Data Index: 418834 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4098. Min Act: -0.0000

Data Index: 914932 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4170. Min Act: 0.0000

Data Index: 785134 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4409. Min Act: 0.0000

Data Index: 46811 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1159795 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1778066 (The Pile)

Max Activating Token Index: 838

Text #16

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3984. Min Act: 0.0000

Data Index: 587826 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3677. Min Act: 0.0000

Data Index: 359986 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3686. Min Act: 0.0000

Data Index: 585343 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1346878 (The Pile)

Max Activating Token Index: 631