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

Dataset: The Pile

Neuron 5119 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1270. Min Range: -1.1270

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1413104 (The Pile)

Max Activating Token Index: 32

Text #1

Max Range: 1.1270. Min Range: -1.1270

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1523295 (The Pile)

Max Activating Token Index: 346

Text #2

Max Range: 1.1270. Min Range: -1.1270

Max Act: 1.0033. Min Act: -0.0000

Data Index: 762404 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 1.1270. Min Range: -1.1270

Max Act: 1.0130. Min Act: -0.0000

Data Index: 163501 (The Pile)

Max Activating Token Index: 22

Text #4

Max Range: 1.1270. Min Range: -1.1270

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1496920 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9764. Min Act: -0.0000

Data Index: 677370 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1698246 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9973. Min Act: -0.0000

Data Index: 1202897 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1123469 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 1.1270. Min Range: -1.1270

Max Act: 1.0311. Min Act: -0.0000

Data Index: 1010361 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 1.1270. Min Range: -1.1270

Max Act: 1.0226. Min Act: -0.0000

Data Index: 782879 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9501. Min Act: -0.0000

Data Index: 656215 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9583. Min Act: -0.0000

Data Index: 517204 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1476361 (The Pile)

Max Activating Token Index: 906

Text #14

Max Range: 1.1270. Min Range: -1.1270

Max Act: 1.0157. Min Act: -0.0000

Data Index: 398094 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1337881 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1907562 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 1.1270. Min Range: -1.1270

Max Act: 1.0251. Min Act: -0.0000

Data Index: 320653 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9816. Min Act: -0.0000

Data Index: 861681 (The Pile)

Max Activating Token Index: 453

Text #19

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9196. Min Act: -0.0000

Data Index: 290792 (The Pile)

Max Activating Token Index: 98