Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1234 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.9519. Min Act: -0.0001

Data Index: 680632 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.7619. Min Act: -0.0001

Data Index: 497350 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6746. Min Act: -0.0001

Data Index: 732861 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6774. Min Act: -0.0001

Data Index: 742305 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6550. Min Act: -0.0001

Data Index: 794478 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6739. Min Act: -0.0001

Data Index: 1134585 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.7034. Min Act: -0.0001

Data Index: 979016 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6261. Min Act: -0.0001

Data Index: 828313 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6572. Min Act: -0.0001

Data Index: 907623 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6537. Min Act: -0.0001

Data Index: 1102934 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6499. Min Act: -0.0001

Data Index: 318405 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6171. Min Act: -0.0001

Data Index: 1131447 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6384. Min Act: -0.0001

Data Index: 1279495 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.5380. Min Act: -0.0001

Data Index: 508342 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6390. Min Act: -0.0001

Data Index: 188418 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.5960. Min Act: -0.0001

Data Index: 1166761 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.5911. Min Act: -0.0001

Data Index: 1018216 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6087. Min Act: -0.0001

Data Index: 891182 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.6240. Min Act: -0.0001

Data Index: 88554 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.9519. Min Range: -0.9519

Max Act: 0.5320. Min Act: -0.0001

Data Index: 206120 (C4 (Web Text))

Max Activating Token Index: 551