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

Dataset: The Pile

Neuron 3806 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.9230. Min Act: 0.0002

Data Index: 1969121 (The Pile)

Max Activating Token Index: 499

Text #1

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.4921. Min Act: -0.0000

Data Index: 38918 (The Pile)

Max Activating Token Index: 48

Text #2

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.0847. Min Act: -0.0000

Data Index: 1854544 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.2555. Min Act: -0.0000

Data Index: 1778763 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.3572. Min Act: -0.0000

Data Index: 1649292 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.9910. Min Act: -0.0000

Data Index: 215280 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.9854. Min Act: -0.0000

Data Index: 1557006 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.0867. Min Act: -0.0000

Data Index: 1174890 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.9293. Min Act: -0.0000

Data Index: 777842 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.9206. Min Act: -0.0000

Data Index: 1731527 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.9049. Min Act: -0.0000

Data Index: 1161698 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.0323. Min Act: 0.0000

Data Index: 1770705 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.0026. Min Act: -0.0000

Data Index: 607954 (The Pile)

Max Activating Token Index: 973

Text #13

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.0041. Min Act: -0.0000

Data Index: 393171 (The Pile)

Max Activating Token Index: 644

Text #14

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.0109. Min Act: 0.0000

Data Index: 1694758 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.9512. Min Act: -0.0000

Data Index: 877496 (The Pile)

Max Activating Token Index: 173

Text #16

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.9362. Min Act: -0.0000

Data Index: 435155 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.1066. Min Act: -0.0000

Data Index: 1761756 (The Pile)

Max Activating Token Index: 132

Text #18

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.9521. Min Act: 0.0000

Data Index: 1250185 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.9375. Min Act: -0.0000

Data Index: 1749924 (The Pile)

Max Activating Token Index: 298