Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2907 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.9151. Min Act: -0.0001

Data Index: 1449991 (Python Code)

Max Activating Token Index: 376

Text #1

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.8377. Min Act: -0.0001

Data Index: 1365505 (Python Code)

Max Activating Token Index: 895

Text #2

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7332. Min Act: -0.0001

Data Index: 738992 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7286. Min Act: -0.0001

Data Index: 1441150 (Python Code)

Max Activating Token Index: 74

Text #4

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1212954 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7323. Min Act: -0.0000

Data Index: 146546 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6687. Min Act: -0.0001

Data Index: 1549453 (Python Code)

Max Activating Token Index: 934

Text #7

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7226. Min Act: -0.0000

Data Index: 273554 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6554. Min Act: -0.0001

Data Index: 1567588 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6694. Min Act: -0.0000

Data Index: 528498 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6490. Min Act: -0.0000

Data Index: 494924 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6270. Min Act: -0.0001

Data Index: 1113174 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6614. Min Act: -0.0001

Data Index: 656009 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6201. Min Act: -0.0001

Data Index: 394981 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1120087 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6356. Min Act: -0.0001

Data Index: 1491532 (Python Code)

Max Activating Token Index: 874

Text #16

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6336. Min Act: -0.0001

Data Index: 1608808 (Python Code)

Max Activating Token Index: 311

Text #17

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6564. Min Act: -0.0001

Data Index: 1538050 (Python Code)

Max Activating Token Index: 434

Text #18

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6087. Min Act: -0.0001

Data Index: 1534772 (Python Code)

Max Activating Token Index: 824

Text #19

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.6248. Min Act: -0.0001

Data Index: 1500418 (Python Code)

Max Activating Token Index: 91