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

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

Neuron 4729 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.4725. Min Act: -0.0000

Data Index: 923623 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1317204 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.3976. Min Act: -0.0000

Data Index: 267227 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.3433. Min Act: -0.0000

Data Index: 814307 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1247325 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1053377 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1217631 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1380522 (Python Code)

Max Activating Token Index: 407

Text #8

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1279733 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.3161. Min Act: -0.0000

Data Index: 410230 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.2976. Min Act: -0.0000

Data Index: 826244 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.2962. Min Act: -0.0000

Data Index: 539279 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1622798 (Python Code)

Max Activating Token Index: 770

Text #13

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1341514 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.2937. Min Act: -0.0000

Data Index: 51490 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.2946. Min Act: -0.0000

Data Index: 240389 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.3028. Min Act: -0.0000

Data Index: 236894 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.2906. Min Act: -0.0000

Data Index: 896630 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1516041 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 0.4725. Min Range: -0.4725

Max Act: 0.2607. Min Act: -0.0000

Data Index: 365529 (C4 (Web Text))

Max Activating Token Index: 429