Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2870 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.3095. Min Act: -0.0001

Data Index: 1071745 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2993. Min Act: -0.0001

Data Index: 1142463 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.3281. Min Act: -0.0001

Data Index: 728974 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2790. Min Act: -0.0001

Data Index: 893040 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2616. Min Act: -0.0001

Data Index: 790675 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2121. Min Act: -0.0001

Data Index: 609051 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1906. Min Act: -0.0001

Data Index: 913409 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2170. Min Act: -0.0001

Data Index: 43496 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1441. Min Act: -0.0001

Data Index: 906691 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2421. Min Act: -0.0001

Data Index: 811202 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2029. Min Act: -0.0001

Data Index: 673605 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2395. Min Act: -0.0001

Data Index: 28296 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2384. Min Act: -0.0001

Data Index: 873547 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1588. Min Act: -0.0001

Data Index: 579644 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1839. Min Act: -0.0001

Data Index: 527090 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2683. Min Act: -0.0001

Data Index: 79890 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1813. Min Act: -0.0001

Data Index: 1209892 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1673. Min Act: -0.0001

Data Index: 528493 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.2047. Min Act: -0.0001

Data Index: 404672 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1583. Min Act: -0.0001

Data Index: 929767 (C4 (Web Text))

Max Activating Token Index: 113