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

Dataset: The Pile

Neuron 3348 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: 0.4964. Min Range: -0.4964

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1995867 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1995741 (The Pile)

Max Activating Token Index: 314

Text #2

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1477659 (The Pile)

Max Activating Token Index: 349

Text #3

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3810. Min Act: -0.0000

Data Index: 1800751 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3787. Min Act: -0.0000

Data Index: 451333 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3701. Min Act: -0.0000

Data Index: 153102 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1168974 (The Pile)

Max Activating Token Index: 107

Text #7

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4064. Min Act: -0.0000

Data Index: 953291 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3808. Min Act: -0.0000

Data Index: 416779 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1143939 (The Pile)

Max Activating Token Index: 597

Text #10

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1888153 (The Pile)

Max Activating Token Index: 716

Text #11

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3925. Min Act: -0.0000

Data Index: 130195 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1828516 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3539. Min Act: -0.0000

Data Index: 169331 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1679032 (The Pile)

Max Activating Token Index: 731

Text #15

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1979982 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3062. Min Act: -0.0000

Data Index: 752351 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3316. Min Act: -0.0000

Data Index: 335507 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3275. Min Act: -0.0000

Data Index: 138347 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 0.4964. Min Range: -0.4964

Max Act: 0.3321. Min Act: -0.0000

Data Index: 835884 (The Pile)

Max Activating Token Index: 814