Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4830 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0504. Min Act: -0.0002

Data Index: 82947 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0440. Min Act: -0.0002

Data Index: 633463 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0441. Min Act: -0.0002

Data Index: 716162 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0450. Min Act: -0.0002

Data Index: 693890 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0425. Min Act: -0.0002

Data Index: 972563 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0415. Min Act: -0.0002

Data Index: 609469 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0415. Min Act: -0.0002

Data Index: 533597 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0413. Min Act: -0.0002

Data Index: 791487 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0408. Min Act: -0.0002

Data Index: 15103 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0413. Min Act: -0.0002

Data Index: 138694 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0390. Min Act: -0.0002

Data Index: 674823 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0392. Min Act: -0.0002

Data Index: 265065 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1242124 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0390. Min Act: -0.0002

Data Index: 644375 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0387. Min Act: -0.0002

Data Index: 325694 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1279001 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0392. Min Act: -0.0002

Data Index: 371613 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1117538 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0390. Min Act: -0.0002

Data Index: 21815 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0386. Min Act: -0.0002

Data Index: 310604 (C4 (Web Text))

Max Activating Token Index: 514