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

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

Neuron 4500 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6533. Min Range: -4.6533

Max Act: 4.5019. Min Act: -0.0000

Data Index: 1328853 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 4.6533. Min Range: -4.6533

Max Act: 4.6533. Min Act: -0.0000

Data Index: 702614 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 4.6533. Min Range: -4.6533

Max Act: 4.3715. Min Act: -0.0000

Data Index: 229478 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 4.6533. Min Range: -4.6533

Max Act: 4.3764. Min Act: -0.0000

Data Index: 666855 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 4.6533. Min Range: -4.6533

Max Act: 3.9853. Min Act: -0.0000

Data Index: 1227315 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 4.6533. Min Range: -4.6533

Max Act: 4.1327. Min Act: -0.0000

Data Index: 686882 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 4.6533. Min Range: -4.6533

Max Act: 4.2598. Min Act: -0.0000

Data Index: 732964 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 4.6533. Min Range: -4.6533

Max Act: 4.3786. Min Act: -0.0000

Data Index: 854164 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 4.6533. Min Range: -4.6533

Max Act: 3.7999. Min Act: -0.0000

Data Index: 625863 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 4.6533. Min Range: -4.6533

Max Act: 4.0943. Min Act: -0.0000

Data Index: 1141326 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 4.6533. Min Range: -4.6533

Max Act: 4.0666. Min Act: -0.0000

Data Index: 429022 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 4.6533. Min Range: -4.6533

Max Act: 3.9680. Min Act: -0.0000

Data Index: 323765 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 4.6533. Min Range: -4.6533

Max Act: 3.9037. Min Act: -0.0000

Data Index: 974046 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 4.6533. Min Range: -4.6533

Max Act: 4.0703. Min Act: -0.0000

Data Index: 535748 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 4.6533. Min Range: -4.6533

Max Act: 3.5033. Min Act: -0.0000

Data Index: 1108719 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 4.6533. Min Range: -4.6533

Max Act: 3.8245. Min Act: -0.0000

Data Index: 626139 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 4.6533. Min Range: -4.6533

Max Act: 3.4765. Min Act: -0.0000

Data Index: 454729 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 4.6533. Min Range: -4.6533

Max Act: 3.5348. Min Act: -0.0000

Data Index: 463099 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 4.6533. Min Range: -4.6533

Max Act: 3.9863. Min Act: -0.0000

Data Index: 1246675 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 4.6533. Min Range: -4.6533

Max Act: 3.8221. Min Act: -0.0000

Data Index: 726767 (C4 (Web Text))

Max Activating Token Index: 230