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

Dataset: The Pile

Neuron 2513 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.4329. Min Act: 0.0000

Data Index: 832620 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1784925 (The Pile)

Max Activating Token Index: 971

Text #2

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3989. Min Act: 0.0000

Data Index: 1909724 (The Pile)

Max Activating Token Index: 1017

Text #3

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1725648 (The Pile)

Max Activating Token Index: 318

Text #4

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3939. Min Act: 0.0000

Data Index: 1879037 (The Pile)

Max Activating Token Index: 1003

Text #5

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3534. Min Act: -0.0001

Data Index: 1688869 (The Pile)

Max Activating Token Index: 851

Text #6

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1266931 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3508. Min Act: -0.0000

Data Index: 507230 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3304. Min Act: 0.0000

Data Index: 426377 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1556431 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3447. Min Act: 0.0000

Data Index: 1175093 (The Pile)

Max Activating Token Index: 391

Text #11

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1548791 (The Pile)

Max Activating Token Index: 833

Text #12

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1669457 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3182. Min Act: -0.0000

Data Index: 1574307 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3154. Min Act: -0.0000

Data Index: 169492 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1233553 (The Pile)

Max Activating Token Index: 470

Text #16

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2695. Min Act: -0.0001

Data Index: 227531 (The Pile)

Max Activating Token Index: 478

Text #17

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1209805 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3070. Min Act: 0.0000

Data Index: 74291 (The Pile)

Max Activating Token Index: 384

Text #19

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3084. Min Act: -0.0000

Data Index: 939096 (The Pile)

Max Activating Token Index: 272