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

Dataset: The Pile

Neuron 3913 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: 0.9814. Min Range: -0.9814

Max Act: 0.9144. Min Act: -0.0000

Data Index: 436759 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1650218 (The Pile)

Max Activating Token Index: 550

Text #2

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1866827 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1196317 (The Pile)

Max Activating Token Index: 396

Text #4

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1702130 (The Pile)

Max Activating Token Index: 438

Text #5

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1365837 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1113213 (The Pile)

Max Activating Token Index: 586

Text #7

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8994. Min Act: -0.0000

Data Index: 1612143 (The Pile)

Max Activating Token Index: 919

Text #8

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8821. Min Act: -0.0000

Data Index: 791512 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1845016 (The Pile)

Max Activating Token Index: 210

Text #10

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1680157 (The Pile)

Max Activating Token Index: 607

Text #11

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1984885 (The Pile)

Max Activating Token Index: 470

Text #12

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1379899 (The Pile)

Max Activating Token Index: 717

Text #13

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.8075. Min Act: -0.0000

Data Index: 589652 (The Pile)

Max Activating Token Index: 239

Text #14

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7653. Min Act: -0.0000

Data Index: 56408 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7928. Min Act: -0.0000

Data Index: 314339 (The Pile)

Max Activating Token Index: 803

Text #16

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7829. Min Act: -0.0000

Data Index: 1639888 (The Pile)

Max Activating Token Index: 162

Text #17

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1966777 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1785651 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 0.9814. Min Range: -0.9814

Max Act: 0.7507. Min Act: -0.0000

Data Index: 404635 (The Pile)

Max Activating Token Index: 50