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

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

Neuron 3256 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0546. Min Act: -0.0003

Data Index: 471584 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0563. Min Act: -0.0003

Data Index: 42484 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0507. Min Act: -0.0003

Data Index: 554674 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0483. Min Act: -0.0003

Data Index: 835760 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0479. Min Act: -0.0003

Data Index: 791918 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0484. Min Act: -0.0003

Data Index: 772410 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0468. Min Act: -0.0003

Data Index: 131867 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0448. Min Act: -0.0003

Data Index: 380112 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0467. Min Act: -0.0003

Data Index: 692254 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0473. Min Act: -0.0003

Data Index: 192662 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0461. Min Act: -0.0002

Data Index: 885744 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1083180 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1127898 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0415. Min Act: -0.0003

Data Index: 613134 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0435. Min Act: -0.0003

Data Index: 163726 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0425. Min Act: -0.0003

Data Index: 467602 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0418. Min Act: -0.0003

Data Index: 908997 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0432. Min Act: -0.0003

Data Index: 709694 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0429. Min Act: -0.0003

Data Index: 424166 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1053612 (C4 (Web Text))

Max Activating Token Index: 164