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

Dataset: The Pile

Neuron 2011 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: 11.8991. Min Range: -11.8991

Max Act: 11.8287. Min Act: -0.0000

Data Index: 1958894 (The Pile)

Max Activating Token Index: 165

Text #1

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.8991. Min Act: -0.0000

Data Index: 363633 (The Pile)

Max Activating Token Index: 779

Text #2

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.8037. Min Act: -0.0000

Data Index: 1941163 (The Pile)

Max Activating Token Index: 411

Text #3

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.5778. Min Act: -0.0000

Data Index: 1097968 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.5637. Min Act: -0.0000

Data Index: 53889 (The Pile)

Max Activating Token Index: 379

Text #5

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.5164. Min Act: -0.0000

Data Index: 1833181 (The Pile)

Max Activating Token Index: 125

Text #6

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.5693. Min Act: -0.0000

Data Index: 1883851 (The Pile)

Max Activating Token Index: 310

Text #7

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.7212. Min Act: -0.0000

Data Index: 939012 (The Pile)

Max Activating Token Index: 874

Text #8

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.1306. Min Act: -0.0000

Data Index: 727637 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.4287. Min Act: -0.0000

Data Index: 386388 (The Pile)

Max Activating Token Index: 900

Text #10

Max Range: 11.8991. Min Range: -11.8991

Max Act: 10.9538. Min Act: -0.0000

Data Index: 907422 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.2568. Min Act: -0.0000

Data Index: 241354 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.4591. Min Act: -0.0000

Data Index: 1546509 (The Pile)

Max Activating Token Index: 287

Text #13

Max Range: 11.8991. Min Range: -11.8991

Max Act: 10.8760. Min Act: -0.0000

Data Index: 952727 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.1149. Min Act: -0.0000

Data Index: 1368370 (The Pile)

Max Activating Token Index: 345

Text #15

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.1278. Min Act: -0.0000

Data Index: 837645 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 11.8991. Min Range: -11.8991

Max Act: 10.9319. Min Act: -0.0000

Data Index: 361996 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.4749. Min Act: -0.0000

Data Index: 700752 (The Pile)

Max Activating Token Index: 873

Text #18

Max Range: 11.8991. Min Range: -11.8991

Max Act: 10.9636. Min Act: -0.0000

Data Index: 1598630 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 11.8991. Min Range: -11.8991

Max Act: 11.2566. Min Act: -0.0000

Data Index: 1783433 (The Pile)

Max Activating Token Index: 803