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

Dataset: The Pile

Neuron 468 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.4110. Min Act: -0.0000

Data Index: 227854 (The Pile)

Max Activating Token Index: 598

Text #1

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1277548 (The Pile)

Max Activating Token Index: 833

Text #2

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3574. Min Act: -0.0000

Data Index: 780528 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3560. Min Act: -0.0000

Data Index: 110051 (The Pile)

Max Activating Token Index: 65

Text #4

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3723. Min Act: -0.0000

Data Index: 583834 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3163. Min Act: -0.0000

Data Index: 716857 (The Pile)

Max Activating Token Index: 70

Text #6

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1010397 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1860657 (The Pile)

Max Activating Token Index: 346

Text #8

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1608869 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1874800 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3272. Min Act: -0.0000

Data Index: 771754 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3337. Min Act: -0.0000

Data Index: 1232253 (The Pile)

Max Activating Token Index: 959

Text #12

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1412065 (The Pile)

Max Activating Token Index: 835

Text #13

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1786621 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3159. Min Act: -0.0000

Data Index: 588291 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1159077 (The Pile)

Max Activating Token Index: 552

Text #16

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3021. Min Act: -0.0000

Data Index: 229108 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3137. Min Act: -0.0000

Data Index: 209642 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1895434 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3137. Min Act: -0.0000

Data Index: 347918 (The Pile)

Max Activating Token Index: 129