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

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

Neuron 392 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0562. Min Act: -0.0002

Data Index: 989216 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0546. Min Act: -0.0002

Data Index: 41967 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0537. Min Act: -0.0003

Data Index: 685581 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0513. Min Act: -0.0002

Data Index: 872641 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0528. Min Act: -0.0003

Data Index: 124427 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0458. Min Act: -0.0002

Data Index: 758514 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0450. Min Act: -0.0002

Data Index: 839201 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1426 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0426. Min Act: -0.0003

Data Index: 815782 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1257704 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0420. Min Act: -0.0003

Data Index: 729183 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0418. Min Act: -0.0002

Data Index: 622039 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0425. Min Act: -0.0003

Data Index: 212177 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0415. Min Act: -0.0002

Data Index: 106347 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0411. Min Act: -0.0002

Data Index: 917803 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1630188 (Python Code)

Max Activating Token Index: 105

Text #16

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1090269 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0398. Min Act: -0.0002

Data Index: 864345 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0406. Min Act: -0.0002

Data Index: 649706 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0404. Min Act: -0.0002

Data Index: 245125 (C4 (Web Text))

Max Activating Token Index: 58