Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3412 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6937. Min Act: -0.0001

Data Index: 209483 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6633. Min Act: -0.0001

Data Index: 1174511 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6468. Min Act: -0.0001

Data Index: 549910 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6647. Min Act: -0.0001

Data Index: 192989 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6402. Min Act: -0.0000

Data Index: 484942 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6412. Min Act: -0.0000

Data Index: 994454 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1218697 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6742. Min Act: -0.0000

Data Index: 525924 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6089. Min Act: -0.0001

Data Index: 1060466 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6317. Min Act: -0.0000

Data Index: 804833 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6418. Min Act: -0.0001

Data Index: 135619 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1194128 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6058. Min Act: -0.0001

Data Index: 1252055 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6236. Min Act: -0.0001

Data Index: 1173761 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6019. Min Act: -0.0001

Data Index: 484821 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6204. Min Act: -0.0000

Data Index: 94967 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1290152 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1331710 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6492. Min Act: -0.0000

Data Index: 601585 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1225768 (C4 (Web Text))

Max Activating Token Index: 740