Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1095 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.7385. Min Act: -0.0000

Data Index: 416713 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.2767. Min Act: -0.0000

Data Index: 271674 (The Pile)

Max Activating Token Index: 518

Text #2

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.3117. Min Act: -0.0000

Data Index: 167021 (The Pile)

Max Activating Token Index: 721

Text #3

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.2645. Min Act: -0.0000

Data Index: 132062 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.2216. Min Act: -0.0000

Data Index: 1379462 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.2079. Min Act: -0.0000

Data Index: 640992 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1672261 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.1835. Min Act: -0.0000

Data Index: 1950442 (The Pile)

Max Activating Token Index: 871

Text #8

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.1247. Min Act: -0.0000

Data Index: 111518 (The Pile)

Max Activating Token Index: 752

Text #9

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.1468. Min Act: -0.0000

Data Index: 803122 (The Pile)

Max Activating Token Index: 261

Text #10

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.1261. Min Act: -0.0000

Data Index: 18609 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1529263 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 1.7385. Min Range: -1.7385

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1252234 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.0537. Min Act: -0.0000

Data Index: 1564034 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1158554 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1972996 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.0967. Min Act: -0.0000

Data Index: 380471 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.0551. Min Act: -0.0000

Data Index: 1304920 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.0639. Min Act: -0.0000

Data Index: 980068 (The Pile)

Max Activating Token Index: 89

Text #19

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.0494. Min Act: -0.0000

Data Index: 1988696 (The Pile)

Max Activating Token Index: 935