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

Dataset: The Pile

Neuron 2571 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: 0.2362. Min Range: -0.2362

Max Act: 0.2249. Min Act: 0.0000

Data Index: 1402232 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2339. Min Act: -0.0000

Data Index: 669680 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2362. Min Act: -0.0000

Data Index: 390763 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2108. Min Act: -0.0000

Data Index: 738238 (The Pile)

Max Activating Token Index: 977

Text #4

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2304. Min Act: -0.0000

Data Index: 918928 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1390996 (The Pile)

Max Activating Token Index: 899

Text #6

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2177. Min Act: -0.0000

Data Index: 782260 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1020717 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1624074 (The Pile)

Max Activating Token Index: 925

Text #9

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2207. Min Act: -0.0000

Data Index: 609909 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1467218 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2081. Min Act: -0.0000

Data Index: 7779 (The Pile)

Max Activating Token Index: 204

Text #12

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1641712 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1311759 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1064464 (The Pile)

Max Activating Token Index: 272

Text #15

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1374560 (The Pile)

Max Activating Token Index: 675

Text #16

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2145. Min Act: -0.0000

Data Index: 556694 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1243626 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2126. Min Act: -0.0000

Data Index: 353212 (The Pile)

Max Activating Token Index: 485

Text #19

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1523861 (The Pile)

Max Activating Token Index: 687