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

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

Neuron 3265 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6379. Min Act: -0.0001

Data Index: 1643262 (Python Code)

Max Activating Token Index: 130

Text #1

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5855. Min Act: -0.0001

Data Index: 1390766 (Python Code)

Max Activating Token Index: 654

Text #2

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5354. Min Act: -0.0001

Data Index: 1540655 (Python Code)

Max Activating Token Index: 158

Text #3

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5167. Min Act: -0.0000

Data Index: 118812 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4754. Min Act: -0.0001

Data Index: 1586784 (Python Code)

Max Activating Token Index: 694

Text #5

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5750. Min Act: -0.0001

Data Index: 1388906 (Python Code)

Max Activating Token Index: 831

Text #6

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4674. Min Act: -0.0001

Data Index: 1548520 (Python Code)

Max Activating Token Index: 313

Text #7

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5133. Min Act: -0.0001

Data Index: 1485534 (Python Code)

Max Activating Token Index: 635

Text #8

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4646. Min Act: -0.0001

Data Index: 1537516 (Python Code)

Max Activating Token Index: 635

Text #9

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4466. Min Act: -0.0001

Data Index: 1525693 (Python Code)

Max Activating Token Index: 978

Text #10

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1437699 (Python Code)

Max Activating Token Index: 167

Text #11

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.3927. Min Act: -0.0001

Data Index: 1554393 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4267. Min Act: -0.0001

Data Index: 1390296 (Python Code)

Max Activating Token Index: 433

Text #13

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4347. Min Act: -0.0000

Data Index: 18396 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4425. Min Act: -0.0001

Data Index: 1393443 (Python Code)

Max Activating Token Index: 533

Text #15

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4187. Min Act: -0.0001

Data Index: 1516718 (Python Code)

Max Activating Token Index: 826

Text #16

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4162. Min Act: -0.0001

Data Index: 1609005 (Python Code)

Max Activating Token Index: 623

Text #17

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4218. Min Act: -0.0001

Data Index: 1511048 (Python Code)

Max Activating Token Index: 530

Text #18

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1637019 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4042. Min Act: -0.0001

Data Index: 1361191 (Python Code)

Max Activating Token Index: 849