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

Dataset: The Pile

Neuron 2027 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.8887. Min Act: -0.0000

Data Index: 668530 (The Pile)

Max Activating Token Index: 72

Text #1

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.3169. Min Act: -0.0000

Data Index: 492158 (The Pile)

Max Activating Token Index: 314

Text #2

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.0332. Min Act: -0.0000

Data Index: 1788383 (The Pile)

Max Activating Token Index: 475

Text #3

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.2945. Min Act: -0.0000

Data Index: 1429267 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.3976. Min Act: -0.0000

Data Index: 1004413 (The Pile)

Max Activating Token Index: 733

Text #5

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.1085. Min Act: -0.0000

Data Index: 1053882 (The Pile)

Max Activating Token Index: 728

Text #6

Max Range: 3.8887. Min Range: -3.8887

Max Act: 2.9314. Min Act: -0.0000

Data Index: 287233 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.1962. Min Act: -0.0000

Data Index: 220346 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.0231. Min Act: -0.0000

Data Index: 1912485 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.0317. Min Act: -0.0000

Data Index: 655551 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.0144. Min Act: -0.0000

Data Index: 1656775 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 3.8887. Min Range: -3.8887

Max Act: 2.9972. Min Act: -0.0000

Data Index: 1789245 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.0465. Min Act: -0.0000

Data Index: 882261 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 3.8887. Min Range: -3.8887

Max Act: 2.8991. Min Act: -0.0000

Data Index: 1879792 (The Pile)

Max Activating Token Index: 193

Text #14

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.0312. Min Act: -0.0000

Data Index: 1100343 (The Pile)

Max Activating Token Index: 77

Text #15

Max Range: 3.8887. Min Range: -3.8887

Max Act: 2.8931. Min Act: -0.0000

Data Index: 126101 (The Pile)

Max Activating Token Index: 524

Text #16

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.0139. Min Act: -0.0000

Data Index: 72823 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 3.8887. Min Range: -3.8887

Max Act: 2.8518. Min Act: -0.0000

Data Index: 1516295 (The Pile)

Max Activating Token Index: 874

Text #18

Max Range: 3.8887. Min Range: -3.8887

Max Act: 2.9796. Min Act: -0.0000

Data Index: 1951469 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 3.8887. Min Range: -3.8887

Max Act: 2.8405. Min Act: -0.0000

Data Index: 1499800 (The Pile)

Max Activating Token Index: 166