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

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

Neuron 2401 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.4190. Min Act: -0.0002

Data Index: 51664 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.4222. Min Act: -0.0002

Data Index: 31645 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3889. Min Act: -0.0002

Data Index: 294163 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3843. Min Act: -0.0002

Data Index: 255950 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3832. Min Act: -0.0002

Data Index: 348706 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3802. Min Act: -0.0002

Data Index: 656646 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3724. Min Act: -0.0002

Data Index: 714637 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3443. Min Act: -0.0002

Data Index: 956963 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3278. Min Act: -0.0002

Data Index: 474577 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3338. Min Act: -0.0002

Data Index: 145537 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3337. Min Act: -0.0002

Data Index: 456508 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3324. Min Act: -0.0002

Data Index: 847553 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3250. Min Act: -0.0002

Data Index: 30341 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3158. Min Act: -0.0002

Data Index: 343458 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3056. Min Act: -0.0002

Data Index: 849451 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2885. Min Act: -0.0002

Data Index: 165474 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2984. Min Act: -0.0002

Data Index: 762673 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.3053. Min Act: -0.0002

Data Index: 154215 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2936. Min Act: -0.0002

Data Index: 283384 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.4222. Min Range: -0.4222

Max Act: 0.2806. Min Act: -0.0002

Data Index: 1055790 (C4 (Web Text))

Max Activating Token Index: 810