Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1026 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3966. Min Act: -0.0001

Data Index: 1198448 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3570. Min Act: -0.0001

Data Index: 936908 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3090. Min Act: -0.0001

Data Index: 1138788 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3318. Min Act: -0.0001

Data Index: 29688 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2943. Min Act: -0.0001

Data Index: 393780 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2979. Min Act: -0.0001

Data Index: 1629331 (Python Code)

Max Activating Token Index: 111

Text #6

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2762. Min Act: -0.0001

Data Index: 638484 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2818. Min Act: -0.0001

Data Index: 960437 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2818. Min Act: -0.0001

Data Index: 1032625 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2814. Min Act: -0.0001

Data Index: 441410 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2758. Min Act: -0.0001

Data Index: 1179928 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2863. Min Act: -0.0001

Data Index: 71379 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2854. Min Act: -0.0001

Data Index: 284731 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2919. Min Act: -0.0001

Data Index: 726522 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2744. Min Act: -0.0001

Data Index: 121073 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2687. Min Act: -0.0001

Data Index: 740729 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2566. Min Act: -0.0001

Data Index: 350727 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2534. Min Act: -0.0001

Data Index: 388223 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2615. Min Act: -0.0001

Data Index: 849627 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.2628. Min Act: -0.0001

Data Index: 458012 (C4 (Web Text))

Max Activating Token Index: 153