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

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

Neuron 985 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1511978 (Python Code)

Max Activating Token Index: 563

Text #1

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.4366. Min Act: -0.0001

Data Index: 1584170 (Python Code)

Max Activating Token Index: 220

Text #2

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1618235 (Python Code)

Max Activating Token Index: 183

Text #3

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3773. Min Act: -0.0001

Data Index: 1523493 (Python Code)

Max Activating Token Index: 606

Text #4

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3614. Min Act: -0.0001

Data Index: 1588956 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1400603 (Python Code)

Max Activating Token Index: 105

Text #6

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3493. Min Act: -0.0001

Data Index: 1638478 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1582581 (Python Code)

Max Activating Token Index: 195

Text #8

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1574725 (Python Code)

Max Activating Token Index: 733

Text #9

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1598576 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3253. Min Act: -0.0001

Data Index: 1521916 (Python Code)

Max Activating Token Index: 165

Text #11

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1374619 (Python Code)

Max Activating Token Index: 548

Text #12

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3205. Min Act: -0.0001

Data Index: 1485092 (Python Code)

Max Activating Token Index: 151

Text #13

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3083. Min Act: -0.0001

Data Index: 1393918 (Python Code)

Max Activating Token Index: 353

Text #14

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1415092 (Python Code)

Max Activating Token Index: 38

Text #15

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1418324 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1643400 (Python Code)

Max Activating Token Index: 282

Text #17

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1638249 (Python Code)

Max Activating Token Index: 736

Text #18

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1567024 (Python Code)

Max Activating Token Index: 565

Text #19

Max Range: 0.4623. Min Range: -0.4623

Max Act: 0.2968. Min Act: -0.0001

Data Index: 1540962 (Python Code)

Max Activating Token Index: 737