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

Dataset: The Pile

Neuron 2402 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: 1.8993. Min Range: -1.8993

Max Act: 1.8993. Min Act: -0.0000

Data Index: 1228414 (The Pile)

Max Activating Token Index: 513

Text #1

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.8799. Min Act: -0.0000

Data Index: 1356661 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.8877. Min Act: -0.0000

Data Index: 959963 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.5554. Min Act: -0.0000

Data Index: 1539348 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.4602. Min Act: -0.0000

Data Index: 288073 (The Pile)

Max Activating Token Index: 867

Text #5

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.4401. Min Act: 0.0000

Data Index: 98457 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.4039. Min Act: -0.0000

Data Index: 1441524 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.4751. Min Act: -0.0000

Data Index: 1248450 (The Pile)

Max Activating Token Index: 168

Text #8

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.5168. Min Act: -0.0000

Data Index: 427225 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3814. Min Act: -0.0000

Data Index: 1276430 (The Pile)

Max Activating Token Index: 197

Text #10

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3126. Min Act: -0.0000

Data Index: 1617226 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.4925. Min Act: -0.0000

Data Index: 378965 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3892. Min Act: -0.0000

Data Index: 102383 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3879. Min Act: -0.0000

Data Index: 509165 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.2462. Min Act: -0.0000

Data Index: 351495 (The Pile)

Max Activating Token Index: 132

Text #15

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3750. Min Act: -0.0000

Data Index: 1973376 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1863985 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3524. Min Act: -0.0000

Data Index: 839445 (The Pile)

Max Activating Token Index: 767

Text #18

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3453. Min Act: -0.0000

Data Index: 1723651 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.3256. Min Act: -0.0000

Data Index: 54037 (The Pile)

Max Activating Token Index: 782