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

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

Neuron 4969 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.1897. Min Act: -0.0000

Data Index: 644381 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.0572. Min Act: -0.0000

Data Index: 829179 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.0500. Min Act: -0.0000

Data Index: 953345 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8673. Min Act: -0.0000

Data Index: 831083 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9056. Min Act: -0.0000

Data Index: 355434 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1116473 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9584. Min Act: -0.0000

Data Index: 297479 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9569. Min Act: -0.0000

Data Index: 327834 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9234. Min Act: -0.0000

Data Index: 701272 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8635. Min Act: -0.0000

Data Index: 587410 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1100647 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8364. Min Act: -0.0000

Data Index: 322213 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8309. Min Act: -0.0000

Data Index: 730972 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1102621 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1081964 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.7821. Min Act: -0.0000

Data Index: 827379 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8110. Min Act: -0.0000

Data Index: 26874 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1171987 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.7978. Min Act: -0.0000

Data Index: 702172 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1193424 (C4 (Web Text))

Max Activating Token Index: 309