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

Dataset: The Pile

Neuron 1696 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: 1.8020. Min Range: -1.8020

Max Act: 1.8020. Min Act: -0.0000

Data Index: 1042970 (The Pile)

Max Activating Token Index: 425

Text #1

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6788. Min Act: -0.0000

Data Index: 1869427 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.7502. Min Act: -0.0000

Data Index: 537306 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6734. Min Act: -0.0000

Data Index: 1384216 (The Pile)

Max Activating Token Index: 523

Text #4

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.6044. Min Act: -0.0000

Data Index: 1285242 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.5699. Min Act: -0.0000

Data Index: 1065235 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.5509. Min Act: -0.0000

Data Index: 1265508 (The Pile)

Max Activating Token Index: 71

Text #7

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.4467. Min Act: -0.0000

Data Index: 598891 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.3712. Min Act: -0.0000

Data Index: 135062 (The Pile)

Max Activating Token Index: 968

Text #9

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.4593. Min Act: -0.0000

Data Index: 1427133 (The Pile)

Max Activating Token Index: 957

Text #10

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.4481. Min Act: -0.0000

Data Index: 1690231 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.2406. Min Act: -0.0000

Data Index: 1688661 (The Pile)

Max Activating Token Index: 655

Text #12

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.4306. Min Act: -0.0000

Data Index: 1375967 (The Pile)

Max Activating Token Index: 489

Text #13

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.4223. Min Act: -0.0000

Data Index: 742709 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.4024. Min Act: -0.0000

Data Index: 797061 (The Pile)

Max Activating Token Index: 429

Text #15

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.3479. Min Act: -0.0000

Data Index: 418582 (The Pile)

Max Activating Token Index: 417

Text #16

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.3786. Min Act: -0.0000

Data Index: 1111511 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.3368. Min Act: -0.0000

Data Index: 747805 (The Pile)

Max Activating Token Index: 946

Text #18

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.3246. Min Act: -0.0000

Data Index: 26688 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.2835. Min Act: -0.0000

Data Index: 628648 (The Pile)

Max Activating Token Index: 90