Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4849 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4863. Min Range: -3.4863

Max Act: 3.4863. Min Act: -0.0000

Data Index: 1252079 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 3.4863. Min Range: -3.4863

Max Act: 3.1069. Min Act: -0.0001

Data Index: 592389 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.7669. Min Act: -0.0000

Data Index: 26424 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.7965. Min Act: -0.0000

Data Index: 839056 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.5927. Min Act: -0.0000

Data Index: 368944 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.7618. Min Act: -0.0000

Data Index: 1301914 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.5896. Min Act: -0.0000

Data Index: 875265 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.4690. Min Act: -0.0000

Data Index: 149965 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.4096. Min Act: -0.0000

Data Index: 321817 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.3716. Min Act: -0.0000

Data Index: 199764 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.2173. Min Act: -0.0000

Data Index: 389139 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.3305. Min Act: -0.0000

Data Index: 474478 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.2035. Min Act: -0.0000

Data Index: 185869 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.1871. Min Act: -0.0000

Data Index: 990612 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.0636. Min Act: -0.0000

Data Index: 843847 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.0418. Min Act: -0.0000

Data Index: 394066 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.1688. Min Act: -0.0000

Data Index: 106261 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.1563. Min Act: -0.0000

Data Index: 660066 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.1356. Min Act: -0.0000

Data Index: 801619 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 3.4863. Min Range: -3.4863

Max Act: 2.0976. Min Act: -0.0000

Data Index: 970479 (C4 (Web Text))

Max Activating Token Index: 340