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

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

Neuron 1992 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: 0.9463. Min Range: -0.9463

Max Act: 0.9463. Min Act: -0.0001

Data Index: 181867 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8768. Min Act: -0.0001

Data Index: 660890 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7665. Min Act: -0.0001

Data Index: 326228 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7722. Min Act: -0.0001

Data Index: 1024615 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6876. Min Act: -0.0001

Data Index: 640970 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7261. Min Act: -0.0001

Data Index: 795154 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7247. Min Act: -0.0001

Data Index: 200532 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6742. Min Act: -0.0001

Data Index: 675636 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6925. Min Act: -0.0001

Data Index: 450404 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6368. Min Act: -0.0001

Data Index: 137967 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6833. Min Act: -0.0001

Data Index: 118617 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7479. Min Act: -0.0001

Data Index: 812845 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5846. Min Act: -0.0001

Data Index: 964235 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6604. Min Act: -0.0001

Data Index: 542944 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5749. Min Act: -0.0001

Data Index: 718981 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6185. Min Act: -0.0001

Data Index: 673651 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6249. Min Act: -0.0001

Data Index: 1260808 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1009682 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6333. Min Act: -0.0001

Data Index: 369972 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.5948. Min Act: -0.0001

Data Index: 1020350 (C4 (Web Text))

Max Activating Token Index: 364