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

Dataset: The Pile

Neuron 618 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: 0.5212. Min Range: -0.5212

Max Act: 0.5212. Min Act: -0.0000

Data Index: 833688 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1256339 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.5108. Min Act: -0.0000

Data Index: 18342 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1468009 (The Pile)

Max Activating Token Index: 335

Text #4

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4098. Min Act: -0.0000

Data Index: 926121 (The Pile)

Max Activating Token Index: 209

Text #5

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4229. Min Act: -0.0000

Data Index: 428067 (The Pile)

Max Activating Token Index: 840

Text #6

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1584390 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3964. Min Act: -0.0000

Data Index: 344454 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1459224 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1090322 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3664. Min Act: -0.0000

Data Index: 317749 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1235778 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3481. Min Act: -0.0000

Data Index: 132344 (The Pile)

Max Activating Token Index: 99

Text #13

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1862617 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3684. Min Act: -0.0000

Data Index: 767350 (The Pile)

Max Activating Token Index: 591

Text #15

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1302565 (The Pile)

Max Activating Token Index: 532

Text #16

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3499. Min Act: -0.0000

Data Index: 973071 (The Pile)

Max Activating Token Index: 84

Text #17

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1380430 (The Pile)

Max Activating Token Index: 793

Text #18

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1260063 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1677790 (The Pile)

Max Activating Token Index: 508