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

Dataset: The Pile

Neuron 1534 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: 0.5359. Min Range: -0.5359

Max Act: 0.5248. Min Act: -0.0000

Data Index: 822554 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.5359. Min Act: -0.0000

Data Index: 748529 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.5074. Min Act: -0.0000

Data Index: 987782 (The Pile)

Max Activating Token Index: 43

Text #3

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4712. Min Act: -0.0000

Data Index: 895912 (The Pile)

Max Activating Token Index: 288

Text #4

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4651. Min Act: -0.0000

Data Index: 138660 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4550. Min Act: -0.0000

Data Index: 278491 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1833484 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4431. Min Act: -0.0000

Data Index: 190686 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1773699 (The Pile)

Max Activating Token Index: 959

Text #9

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1990730 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4224. Min Act: -0.0000

Data Index: 724332 (The Pile)

Max Activating Token Index: 522

Text #11

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4561. Min Act: -0.0000

Data Index: 738591 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1760930 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1686421 (The Pile)

Max Activating Token Index: 947

Text #14

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4275. Min Act: -0.0000

Data Index: 873783 (The Pile)

Max Activating Token Index: 353

Text #15

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4397. Min Act: -0.0000

Data Index: 830179 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1088624 (The Pile)

Max Activating Token Index: 966

Text #17

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1652369 (The Pile)

Max Activating Token Index: 981

Text #18

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.4349. Min Act: -0.0000

Data Index: 599228 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3907. Min Act: -0.0000

Data Index: 1369136 (The Pile)

Max Activating Token Index: 845