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

Dataset: The Pile

Neuron 1315 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: 1.2323. Min Range: -1.2323

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1592939 (The Pile)

Max Activating Token Index: 634

Text #1

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.1450. Min Act: -0.0000

Data Index: 1411491 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.0252. Min Act: -0.0000

Data Index: 924886 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1327994 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1220140 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1414575 (The Pile)

Max Activating Token Index: 560

Text #6

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9712. Min Act: -0.0000

Data Index: 293492 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9628. Min Act: -0.0000

Data Index: 951451 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1976335 (The Pile)

Max Activating Token Index: 981

Text #9

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9457. Min Act: -0.0000

Data Index: 1903143 (The Pile)

Max Activating Token Index: 1002

Text #10

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1652490 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1388826 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9402. Min Act: -0.0000

Data Index: 1101144 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1010554 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9117. Min Act: -0.0000

Data Index: 300518 (The Pile)

Max Activating Token Index: 556

Text #15

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1674228 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9435. Min Act: -0.0000

Data Index: 819933 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8802. Min Act: -0.0000

Data Index: 96048 (The Pile)

Max Activating Token Index: 302

Text #18

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1159973 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9026. Min Act: -0.0000

Data Index: 80033 (The Pile)

Max Activating Token Index: 517