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

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

Neuron 5225 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: 2.2915. Min Range: -2.2915

Max Act: 2.2915. Min Act: -0.0000

Data Index: 461862 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.2649. Min Act: -0.0000

Data Index: 306776 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.2551. Min Act: -0.0000

Data Index: 1307329 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.2331. Min Act: -0.0000

Data Index: 518558 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.1031. Min Act: -0.0000

Data Index: 1158784 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.1969. Min Act: -0.0000

Data Index: 205208 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.0708. Min Act: -0.0000

Data Index: 17162 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.1576. Min Act: -0.0000

Data Index: 364934 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.2838. Min Act: -0.0000

Data Index: 1139376 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.1177. Min Act: -0.0000

Data Index: 577820 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.0898. Min Act: -0.0000

Data Index: 791027 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.0982. Min Act: -0.0000

Data Index: 482255 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.0798. Min Act: -0.0000

Data Index: 770560 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.1052. Min Act: -0.0000

Data Index: 822883 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.0979. Min Act: -0.0000

Data Index: 886726 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 2.2915. Min Range: -2.2915

Max Act: 1.9630. Min Act: -0.0000

Data Index: 457880 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.0051. Min Act: -0.0000

Data Index: 389160 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 2.2915. Min Range: -2.2915

Max Act: 2.1341. Min Act: -0.0000

Data Index: 736061 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 2.2915. Min Range: -2.2915

Max Act: 1.9928. Min Act: -0.0000

Data Index: 1341270 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 2.2915. Min Range: -2.2915

Max Act: 1.9682. Min Act: -0.0000

Data Index: 179959 (C4 (Web Text))

Max Activating Token Index: 693