Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2015 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0003

Data Index: 57621 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0494. Min Act: -0.0003

Data Index: 24716 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0483. Min Act: -0.0003

Data Index: 568832 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0463. Min Act: -0.0003

Data Index: 620370 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0442. Min Act: -0.0002

Data Index: 42138 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1325351 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0445. Min Act: -0.0004

Data Index: 841361 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1267757 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0436. Min Act: -0.0004

Data Index: 279797 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0436. Min Act: -0.0003

Data Index: 461675 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1063558 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0423. Min Act: -0.0003

Data Index: 960948 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1197309 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0434. Min Act: -0.0003

Data Index: 919617 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0426. Min Act: -0.0003

Data Index: 228630 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1351489 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0411. Min Act: -0.0003

Data Index: 1242523 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0418. Min Act: -0.0003

Data Index: 902585 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1015723 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0419. Min Act: -0.0003

Data Index: 650 (C4 (Web Text))

Max Activating Token Index: 294