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

Dataset: The Pile

Neuron 2431 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: 1.2332. Min Range: -1.2332

Max Act: 1.0166. Min Act: -0.0000

Data Index: 1269498 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 1.2332. Min Range: -1.2332

Max Act: 1.1581. Min Act: -0.0000

Data Index: 156471 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 1.2332. Min Range: -1.2332

Max Act: 1.2332. Min Act: -0.0000

Data Index: 1683054 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 1.2332. Min Range: -1.2332

Max Act: 1.0781. Min Act: -0.0000

Data Index: 222676 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1335562 (The Pile)

Max Activating Token Index: 1000

Text #5

Max Range: 1.2332. Min Range: -1.2332

Max Act: 1.0035. Min Act: -0.0000

Data Index: 453822 (The Pile)

Max Activating Token Index: 363

Text #6

Max Range: 1.2332. Min Range: -1.2332

Max Act: 1.0040. Min Act: -0.0000

Data Index: 1493262 (The Pile)

Max Activating Token Index: 433

Text #7

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9148. Min Act: -0.0000

Data Index: 749048 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1217508 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1033425 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 1.2332. Min Range: -1.2332

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1611947 (The Pile)

Max Activating Token Index: 158

Text #11

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9626. Min Act: -0.0000

Data Index: 601568 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9917. Min Act: -0.0000

Data Index: 833852 (The Pile)

Max Activating Token Index: 126

Text #13

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9292. Min Act: -0.0000

Data Index: 71726 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9074. Min Act: -0.0000

Data Index: 501092 (The Pile)

Max Activating Token Index: 519

Text #15

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9467. Min Act: -0.0000

Data Index: 931349 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8828. Min Act: -0.0000

Data Index: 551925 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8649. Min Act: -0.0000

Data Index: 527447 (The Pile)

Max Activating Token Index: 920

Text #18

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8333. Min Act: -0.0000

Data Index: 622635 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8566. Min Act: -0.0000

Data Index: 361956 (The Pile)

Max Activating Token Index: 155