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

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

Neuron 3161 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.4090. Min Act: -0.0001

Data Index: 215553 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3651. Min Act: -0.0001

Data Index: 91427 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3661. Min Act: -0.0001

Data Index: 1066499 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3557. Min Act: -0.0001

Data Index: 1594495 (Python Code)

Max Activating Token Index: 468

Text #4

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3232. Min Act: -0.0001

Data Index: 968507 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3791. Min Act: -0.0001

Data Index: 779102 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3307. Min Act: -0.0001

Data Index: 133516 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3060. Min Act: -0.0001

Data Index: 1109494 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2941. Min Act: -0.0001

Data Index: 688812 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3411. Min Act: -0.0001

Data Index: 1222296 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3409. Min Act: -0.0001

Data Index: 1279387 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3273. Min Act: -0.0001

Data Index: 412603 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3154. Min Act: -0.0001

Data Index: 41821 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3160. Min Act: -0.0001

Data Index: 120555 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3354. Min Act: -0.0001

Data Index: 1305203 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2395. Min Act: -0.0001

Data Index: 1067808 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2796. Min Act: -0.0001

Data Index: 811756 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2926. Min Act: -0.0001

Data Index: 1287173 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2827. Min Act: -0.0001

Data Index: 623849 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3001. Min Act: -0.0001

Data Index: 1242077 (C4 (Web Text))

Max Activating Token Index: 154