Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4426 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5527. Min Range: -2.5527

Max Act: 2.5527. Min Act: -0.0000

Data Index: 1098408 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 2.5527. Min Range: -2.5527

Max Act: 2.4869. Min Act: -0.0000

Data Index: 874494 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 2.5527. Min Range: -2.5527

Max Act: 2.3600. Min Act: -0.0000

Data Index: 686161 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 2.5527. Min Range: -2.5527

Max Act: 2.2147. Min Act: -0.0000

Data Index: 465136 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 2.5527. Min Range: -2.5527

Max Act: 2.1085. Min Act: -0.0000

Data Index: 1038289 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 2.5527. Min Range: -2.5527

Max Act: 2.0894. Min Act: -0.0000

Data Index: 796696 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.9265. Min Act: -0.0000

Data Index: 849426 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 2.5527. Min Range: -2.5527

Max Act: 2.0691. Min Act: -0.0000

Data Index: 950465 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.9263. Min Act: -0.0000

Data Index: 529669 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.8177. Min Act: -0.0000

Data Index: 1228336 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.9139. Min Act: -0.0000

Data Index: 1311657 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.9051. Min Act: -0.0000

Data Index: 811238 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.9052. Min Act: -0.0000

Data Index: 786602 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.7791. Min Act: -0.0000

Data Index: 403247 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.9631. Min Act: -0.0000

Data Index: 884583 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.7605. Min Act: -0.0000

Data Index: 377895 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.6568. Min Act: -0.0000

Data Index: 726002 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.7564. Min Act: -0.0000

Data Index: 248520 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.8436. Min Act: -0.0000

Data Index: 1278301 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 2.5527. Min Range: -2.5527

Max Act: 1.7501. Min Act: -0.0000

Data Index: 409122 (C4 (Web Text))

Max Activating Token Index: 77