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

Dataset: The Pile

Neuron 2148 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: 3.0243. Min Range: -3.0243

Max Act: 3.0243. Min Act: -0.0000

Data Index: 1808570 (The Pile)

Max Activating Token Index: 872

Text #1

Max Range: 3.0243. Min Range: -3.0243

Max Act: 2.3002. Min Act: -0.0000

Data Index: 654942 (The Pile)

Max Activating Token Index: 883

Text #2

Max Range: 3.0243. Min Range: -3.0243

Max Act: 2.2752. Min Act: -0.0000

Data Index: 1407292 (The Pile)

Max Activating Token Index: 959

Text #3

Max Range: 3.0243. Min Range: -3.0243

Max Act: 2.0822. Min Act: -0.0000

Data Index: 1109383 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.9065. Min Act: -0.0000

Data Index: 1885431 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.9581. Min Act: -0.0000

Data Index: 1408518 (The Pile)

Max Activating Token Index: 44

Text #6

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.9420. Min Act: 0.0000

Data Index: 37985 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.8431. Min Act: -0.0000

Data Index: 347784 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.6251. Min Act: -0.0000

Data Index: 191533 (The Pile)

Max Activating Token Index: 412

Text #9

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.6757. Min Act: -0.0000

Data Index: 118326 (The Pile)

Max Activating Token Index: 754

Text #10

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.6468. Min Act: -0.0000

Data Index: 186327 (The Pile)

Max Activating Token Index: 767

Text #11

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.5441. Min Act: -0.0000

Data Index: 684683 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.5289. Min Act: -0.0000

Data Index: 267314 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.6302. Min Act: -0.0000

Data Index: 1729847 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.6176. Min Act: -0.0000

Data Index: 1953594 (The Pile)

Max Activating Token Index: 728

Text #15

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.6131. Min Act: -0.0000

Data Index: 27411 (The Pile)

Max Activating Token Index: 312

Text #16

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.5960. Min Act: -0.0000

Data Index: 297531 (The Pile)

Max Activating Token Index: 320

Text #17

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.6016. Min Act: -0.0000

Data Index: 65298 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.4900. Min Act: -0.0000

Data Index: 1809585 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 3.0243. Min Range: -3.0243

Max Act: 1.6719. Min Act: -0.0000

Data Index: 422420 (The Pile)

Max Activating Token Index: 476