Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1606 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.3033. Min Act: -0.0005

Data Index: 392710 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.3003. Min Act: -0.0005

Data Index: 309231 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.3012. Min Act: -0.0005

Data Index: 1026798 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.3014. Min Act: -0.0005

Data Index: 410157 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.3041. Min Act: -0.0005

Data Index: 1312315 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2857. Min Act: -0.0005

Data Index: 1219037 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2614. Min Act: -0.0005

Data Index: 1047707 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2678. Min Act: -0.0005

Data Index: 821671 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2733. Min Act: -0.0005

Data Index: 127688 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2504. Min Act: -0.0005

Data Index: 192024 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2589. Min Act: -0.0005

Data Index: 817968 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2495. Min Act: -0.0005

Data Index: 1199041 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2577. Min Act: -0.0005

Data Index: 192490 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2476. Min Act: -0.0005

Data Index: 15752 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2571. Min Act: -0.0005

Data Index: 1255717 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2412. Min Act: -0.0005

Data Index: 539409 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2425. Min Act: -0.0005

Data Index: 511965 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2598. Min Act: -0.0005

Data Index: 476031 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2386. Min Act: -0.0005

Data Index: 1225156 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2474. Min Act: -0.0005

Data Index: 794928 (C4 (Web Text))

Max Activating Token Index: 979