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

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

Neuron 3952 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: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0002

Data Index: 624041 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0467. Min Act: -0.0003

Data Index: 445480 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1529338 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1293956 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1210479 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1325784 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1580213 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1650072 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1387096 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0377. Min Act: -0.0002

Data Index: 810811 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1619644 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0384. Min Act: -0.0002

Data Index: 542751 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0377. Min Act: -0.0003

Data Index: 428388 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0379. Min Act: -0.0003

Data Index: 301260 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1535770 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0370. Min Act: -0.0003

Data Index: 695436 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0366. Min Act: -0.0002

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0355. Min Act: -0.0003

Data Index: 529094 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0340. Min Act: -0.0002

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1073553 (C4 (Web Text))

Max Activating Token Index: 677