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

Dataset: The Pile

Neuron 3265 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.4021. Min Act: -0.0000

Data Index: 533569 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.3583. Min Act: -0.0000

Data Index: 763048 (The Pile)

Max Activating Token Index: 331

Text #2

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.3026. Min Act: -0.0000

Data Index: 656253 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.3638. Min Act: -0.0000

Data Index: 345844 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2768. Min Act: -0.0000

Data Index: 460023 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2630. Min Act: -0.0000

Data Index: 496365 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2283. Min Act: -0.0000

Data Index: 456894 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2571. Min Act: -0.0000

Data Index: 198514 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2499. Min Act: -0.0000

Data Index: 182939 (The Pile)

Max Activating Token Index: 959

Text #9

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2715. Min Act: -0.0000

Data Index: 6747 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1781122 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2399. Min Act: -0.0000

Data Index: 1210994 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2705. Min Act: -0.0000

Data Index: 1351063 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2262. Min Act: -0.0000

Data Index: 289102 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1879277 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1740316 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2387. Min Act: -0.0000

Data Index: 864003 (The Pile)

Max Activating Token Index: 319

Text #17

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2367. Min Act: -0.0000

Data Index: 658611 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2467. Min Act: -0.0000

Data Index: 174832 (The Pile)

Max Activating Token Index: 217

Text #19

Max Range: 0.4021. Min Range: -0.4021

Max Act: 0.2124. Min Act: -0.0000

Data Index: 793301 (The Pile)

Max Activating Token Index: 1000