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

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

Neuron 1441 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: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0002

Data Index: 954955 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1445602 (Python Code)

Max Activating Token Index: 32

Text #2

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1291567 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1367386 (Python Code)

Max Activating Token Index: 894

Text #4

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0390. Min Act: -0.0002

Data Index: 249014 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0397. Min Act: -0.0002

Data Index: 714787 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1225478 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1560783 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1365262 (Python Code)

Max Activating Token Index: 39

Text #9

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1408540 (Python Code)

Max Activating Token Index: 112

Text #10

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0381. Min Act: -0.0002

Data Index: 78088 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1088444 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1291406 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1493626 (Python Code)

Max Activating Token Index: 253

Text #14

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0366. Min Act: -0.0002

Data Index: 190821 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0355. Min Act: -0.0002

Data Index: 616168 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1431143 (Python Code)

Max Activating Token Index: 642

Text #17

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1476116 (Python Code)

Max Activating Token Index: 1014

Text #18

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1605105 (Python Code)

Max Activating Token Index: 46

Text #19

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0351. Min Act: -0.0002

Data Index: 628373 (C4 (Web Text))

Max Activating Token Index: 1001