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

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

Neuron 3439 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: 1.1262. Min Range: -1.1262

Max Act: 1.1262. Min Act: -0.0001

Data Index: 389900 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9779. Min Act: -0.0001

Data Index: 1255508 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9805. Min Act: -0.0001

Data Index: 1200786 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9730. Min Act: -0.0001

Data Index: 1008615 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9011. Min Act: -0.0001

Data Index: 928763 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9484. Min Act: -0.0001

Data Index: 504251 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9135. Min Act: -0.0001

Data Index: 1255411 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9286. Min Act: -0.0001

Data Index: 606258 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8667. Min Act: -0.0001

Data Index: 1192974 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8886. Min Act: -0.0001

Data Index: 91207 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.9297. Min Act: -0.0001

Data Index: 664104 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.7579. Min Act: -0.0001

Data Index: 463239 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8473. Min Act: -0.0001

Data Index: 70994 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8496. Min Act: -0.0001

Data Index: 1311543 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8506. Min Act: -0.0001

Data Index: 97176 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8082. Min Act: -0.0001

Data Index: 932906 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8664. Min Act: -0.0001

Data Index: 1276542 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8608. Min Act: -0.0001

Data Index: 787687 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.7946. Min Act: -0.0001

Data Index: 352673 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 1.1262. Min Range: -1.1262

Max Act: 0.8111. Min Act: -0.0001

Data Index: 309784 (C4 (Web Text))

Max Activating Token Index: 895