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

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

Neuron 11 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0931. Min Act: -0.0001

Data Index: 355927 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1094700 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0847. Min Act: -0.0001

Data Index: 416245 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0734. Min Act: -0.0001

Data Index: 197918 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0710. Min Act: -0.0001

Data Index: 547597 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1125344 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0664. Min Act: -0.0001

Data Index: 634488 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1239567 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1297607 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0576. Min Act: -0.0001

Data Index: 81531 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1224140 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0578. Min Act: -0.0001

Data Index: 759598 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0623. Min Act: -0.0001

Data Index: 556379 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1131214 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1282753 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0587. Min Act: -0.0001

Data Index: 79926 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0546. Min Act: -0.0001

Data Index: 610200 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0515. Min Act: -0.0001

Data Index: 1014301 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0605. Min Act: -0.0001

Data Index: 19942 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0630. Min Act: -0.0001

Data Index: 734671 (C4 (Web Text))

Max Activating Token Index: 459