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

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

Neuron 365 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: 0.0379. Min Range: -0.0379

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1386802 (Python Code)

Max Activating Token Index: 627

Text #1

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0357. Min Act: -0.0002

Data Index: 685345 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0349. Min Act: -0.0002

Data Index: 610659 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1582947 (Python Code)

Max Activating Token Index: 1004

Text #4

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0336. Min Act: -0.0003

Data Index: 305874 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0325. Min Act: -0.0002

Data Index: 348739 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1228248 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0309. Min Act: -0.0002

Data Index: 131520 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0306. Min Act: -0.0002

Data Index: 427848 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1366076 (Python Code)

Max Activating Token Index: 48

Text #10

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1436599 (Python Code)

Max Activating Token Index: 613

Text #11

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0300. Min Act: -0.0002

Data Index: 659523 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0303. Min Act: -0.0002

Data Index: 19242 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1481780 (Python Code)

Max Activating Token Index: 451

Text #14

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1651939 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1255231 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1407865 (Python Code)

Max Activating Token Index: 680

Text #17

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0292. Min Act: -0.0002

Data Index: 778927 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0296. Min Act: -0.0002

Data Index: 684404 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1562336 (Python Code)

Max Activating Token Index: 905