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

Dataset: The Pile

Neuron 3439 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: 0.3135. Min Range: -0.3135

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1072191 (The Pile)

Max Activating Token Index: 185

Text #1

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2913. Min Act: -0.0000

Data Index: 111062 (The Pile)

Max Activating Token Index: 972

Text #2

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1124248 (The Pile)

Max Activating Token Index: 648

Text #3

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2745. Min Act: -0.0000

Data Index: 564288 (The Pile)

Max Activating Token Index: 220

Text #4

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2859. Min Act: -0.0000

Data Index: 825992 (The Pile)

Max Activating Token Index: 214

Text #5

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2735. Min Act: -0.0000

Data Index: 278264 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2493. Min Act: -0.0000

Data Index: 865488 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2418. Min Act: -0.0000

Data Index: 404421 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2728. Min Act: -0.0000

Data Index: 67992 (The Pile)

Max Activating Token Index: 54

Text #9

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1270494 (The Pile)

Max Activating Token Index: 942

Text #10

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2398. Min Act: -0.0000

Data Index: 657634 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2335. Min Act: -0.0000

Data Index: 878195 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1625099 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1334658 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1497246 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2399. Min Act: -0.0000

Data Index: 1342553 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2252. Min Act: -0.0000

Data Index: 335524 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2233. Min Act: -0.0000

Data Index: 496956 (The Pile)

Max Activating Token Index: 523

Text #18

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1341946 (The Pile)

Max Activating Token Index: 954

Text #19

Max Range: 0.3135. Min Range: -0.3135

Max Act: 0.2538. Min Act: -0.0000

Data Index: 883464 (The Pile)

Max Activating Token Index: 516