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

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

Neuron 1355 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: 0.3216. Min Range: -0.3216

Max Act: 0.3216. Min Act: -0.0001

Data Index: 330073 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2947. Min Act: -0.0001

Data Index: 53415 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2939. Min Act: -0.0001

Data Index: 1045714 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2812. Min Act: -0.0001

Data Index: 462237 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2819. Min Act: -0.0001

Data Index: 387231 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2793. Min Act: -0.0001

Data Index: 328365 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2678. Min Act: -0.0001

Data Index: 1059433 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2598. Min Act: -0.0001

Data Index: 740195 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2798. Min Act: -0.0001

Data Index: 1064516 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2663. Min Act: -0.0001

Data Index: 221229 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2648. Min Act: -0.0001

Data Index: 574903 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2738. Min Act: -0.0001

Data Index: 1284622 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2745. Min Act: -0.0001

Data Index: 68649 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2701. Min Act: -0.0001

Data Index: 451065 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2449. Min Act: -0.0001

Data Index: 917599 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2716. Min Act: -0.0001

Data Index: 60208 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2628. Min Act: -0.0001

Data Index: 197035 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2720. Min Act: -0.0001

Data Index: 835377 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2810. Min Act: -0.0001

Data Index: 1045498 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.3216. Min Range: -0.3216

Max Act: 0.2662. Min Act: -0.0001

Data Index: 1134788 (C4 (Web Text))

Max Activating Token Index: 929