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

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

Neuron 2670 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: 1.0962. Min Range: -1.0962

Max Act: 1.0962. Min Act: -0.0001

Data Index: 1035775 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 1.0962. Min Range: -1.0962

Max Act: 1.0203. Min Act: -0.0001

Data Index: 781984 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8387. Min Act: -0.0001

Data Index: 566444 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.7633. Min Act: -0.0001

Data Index: 1263647 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.9243. Min Act: -0.0001

Data Index: 69294 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.9344. Min Act: -0.0001

Data Index: 949785 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8231. Min Act: -0.0001

Data Index: 184079 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.7961. Min Act: -0.0001

Data Index: 726971 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8278. Min Act: -0.0001

Data Index: 851766 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.7806. Min Act: -0.0001

Data Index: 950853 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8215. Min Act: -0.0001

Data Index: 422470 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8026. Min Act: -0.0001

Data Index: 550881 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.9203. Min Act: -0.0001

Data Index: 952798 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.7685. Min Act: -0.0001

Data Index: 17228 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8147. Min Act: -0.0001

Data Index: 973970 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8605. Min Act: -0.0001

Data Index: 868086 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8128. Min Act: -0.0001

Data Index: 329806 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.7686. Min Act: -0.0001

Data Index: 516906 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.7993. Min Act: -0.0001

Data Index: 412252 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.7539. Min Act: -0.0001

Data Index: 1211436 (C4 (Web Text))

Max Activating Token Index: 348