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

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

Neuron 4286 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: 2.2848. Min Range: -2.2848

Max Act: 2.2146. Min Act: -0.0000

Data Index: 1140714 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 2.2848. Min Range: -2.2848

Max Act: 2.2848. Min Act: -0.0000

Data Index: 1293195 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 2.2848. Min Range: -2.2848

Max Act: 2.0748. Min Act: -0.0000

Data Index: 520858 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.8208. Min Act: -0.0000

Data Index: 1155166 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.8728. Min Act: -0.0000

Data Index: 233523 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.8359. Min Act: -0.0000

Data Index: 1323448 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.6744. Min Act: -0.0000

Data Index: 19204 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.7039. Min Act: -0.0000

Data Index: 637091 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.7359. Min Act: -0.0000

Data Index: 615543 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.4573. Min Act: -0.0000

Data Index: 491896 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.6069. Min Act: -0.0000

Data Index: 943257 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.5025. Min Act: -0.0000

Data Index: 165661 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.6583. Min Act: -0.0000

Data Index: 262543 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.5828. Min Act: -0.0000

Data Index: 197756 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.6428. Min Act: -0.0000

Data Index: 1065624 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.5399. Min Act: -0.0000

Data Index: 986063 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.5345. Min Act: -0.0000

Data Index: 1107503 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.6096. Min Act: -0.0000

Data Index: 663382 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.5086. Min Act: -0.0000

Data Index: 1242874 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 2.2848. Min Range: -2.2848

Max Act: 1.5151. Min Act: -0.0000

Data Index: 948323 (C4 (Web Text))

Max Activating Token Index: 974