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

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

Neuron 4484 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0580. Min Act: -0.0002

Data Index: 88316 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0507. Min Act: -0.0002

Data Index: 238030 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0513. Min Act: -0.0002

Data Index: 255254 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0459. Min Act: -0.0002

Data Index: 21880 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0454. Min Act: -0.0002

Data Index: 162920 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0450. Min Act: -0.0002

Data Index: 486583 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0468. Min Act: -0.0002

Data Index: 152497 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0464. Min Act: -0.0002

Data Index: 671802 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1130591 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0512. Min Act: -0.0002

Data Index: 40412 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0437. Min Act: -0.0002

Data Index: 643451 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0438. Min Act: -0.0002

Data Index: 20637 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0436. Min Act: -0.0002

Data Index: 753310 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1308394 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0433. Min Act: -0.0002

Data Index: 209715 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0405. Min Act: -0.0002

Data Index: 786315 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0421. Min Act: -0.0002

Data Index: 39892 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1169293 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1284295 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0425. Min Act: -0.0002

Data Index: 749421 (C4 (Web Text))

Max Activating Token Index: 536