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

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

Neuron 951 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0522. Min Range: -2.0522

Max Act: 2.0462. Min Act: -0.0000

Data Index: 1303633 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 2.0522. Min Range: -2.0522

Max Act: 2.0522. Min Act: -0.0000

Data Index: 828139 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.7748. Min Act: -0.0000

Data Index: 1074617 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.8676. Min Act: -0.0000

Data Index: 1212397 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.7900. Min Act: -0.0000

Data Index: 465292 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.7039. Min Act: -0.0000

Data Index: 735708 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.6057. Min Act: -0.0000

Data Index: 320256 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.5662. Min Act: -0.0000

Data Index: 918924 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1012480 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.4734. Min Act: -0.0000

Data Index: 281318 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.3373. Min Act: -0.0000

Data Index: 762471 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.3605. Min Act: -0.0000

Data Index: 133099 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.3766. Min Act: -0.0000

Data Index: 1040853 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.3413. Min Act: -0.0000

Data Index: 388525 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.3088. Min Act: -0.0000

Data Index: 1055381 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.3820. Min Act: -0.0000

Data Index: 1019228 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.2972. Min Act: -0.0000

Data Index: 151200 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.3329. Min Act: -0.0000

Data Index: 1274385 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1324424 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 2.0522. Min Range: -2.0522

Max Act: 1.2772. Min Act: -0.0000

Data Index: 380786 (C4 (Web Text))

Max Activating Token Index: 507