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

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

Neuron 1262 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.8246. Min Act: -0.0000

Data Index: 49091 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.8528. Min Act: -0.0000

Data Index: 42876 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.8463. Min Act: -0.0000

Data Index: 933496 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5233. Min Act: -0.0000

Data Index: 965065 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5579. Min Act: -0.0000

Data Index: 424552 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5404. Min Act: -0.0000

Data Index: 1545496 (Python Code)

Max Activating Token Index: 75

Text #6

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4969. Min Act: -0.0000

Data Index: 172073 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.6283. Min Act: -0.0000

Data Index: 297764 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4768. Min Act: -0.0000

Data Index: 1540409 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4267. Min Act: -0.0000

Data Index: 691694 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5124. Min Act: -0.0000

Data Index: 101813 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.3790. Min Act: -0.0000

Data Index: 106425 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5000. Min Act: -0.0000

Data Index: 606200 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5001. Min Act: -0.0000

Data Index: 29196 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.3783. Min Act: -0.0000

Data Index: 1574093 (Python Code)

Max Activating Token Index: 211

Text #15

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4904. Min Act: -0.0000

Data Index: 809161 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5102. Min Act: -0.0000

Data Index: 353051 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5560. Min Act: -0.0000

Data Index: 1292214 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4582. Min Act: -0.0000

Data Index: 1656379 (Python Code)

Max Activating Token Index: 71

Text #19

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4135. Min Act: -0.0000

Data Index: 514611 (C4 (Web Text))

Max Activating Token Index: 306