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

Dataset: The Pile

Neuron 817 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.5756. Min Act: -0.0000

Data Index: 810499 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.5235. Min Act: -0.0000

Data Index: 766248 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.5539. Min Act: -0.0000

Data Index: 412531 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1554607 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.5486. Min Act: -0.0000

Data Index: 311259 (The Pile)

Max Activating Token Index: 352

Text #5

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4849. Min Act: -0.0000

Data Index: 366777 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1410727 (The Pile)

Max Activating Token Index: 520

Text #7

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1656979 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1195039 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1334361 (The Pile)

Max Activating Token Index: 643

Text #10

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4933. Min Act: -0.0000

Data Index: 907180 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1993528 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1417931 (The Pile)

Max Activating Token Index: 141

Text #13

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1892716 (The Pile)

Max Activating Token Index: 533

Text #14

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1530640 (The Pile)

Max Activating Token Index: 636

Text #15

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1976878 (The Pile)

Max Activating Token Index: 66

Text #16

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1061619 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4956. Min Act: -0.0000

Data Index: 22476 (The Pile)

Max Activating Token Index: 997

Text #18

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1998123 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4780. Min Act: -0.0000

Data Index: 450389 (The Pile)

Max Activating Token Index: 293