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

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

Neuron 5601 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.7048. Min Act: -0.0000

Data Index: 661915 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.5748. Min Act: -0.0000

Data Index: 846018 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.4907. Min Act: -0.0000

Data Index: 1350769 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.6090. Min Act: -0.0000

Data Index: 1302813 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.5910. Min Act: -0.0000

Data Index: 799262 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.5698. Min Act: -0.0000

Data Index: 633016 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.5166. Min Act: -0.0000

Data Index: 1259318 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.4772. Min Act: -0.0000

Data Index: 1241111 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.4407. Min Act: -0.0000

Data Index: 214199 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.3939. Min Act: -0.0000

Data Index: 798297 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.4772. Min Act: -0.0000

Data Index: 22318 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.5153. Min Act: -0.0000

Data Index: 447482 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.3469. Min Act: -0.0000

Data Index: 72239 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.4498. Min Act: -0.0000

Data Index: 80987 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.4190. Min Act: -0.0000

Data Index: 568713 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.3687. Min Act: -0.0000

Data Index: 837498 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.3908. Min Act: -0.0000

Data Index: 704107 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1649328 (Python Code)

Max Activating Token Index: 726

Text #18

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.4175. Min Act: -0.0000

Data Index: 672152 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 1.7048. Min Range: -1.7048

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1275139 (C4 (Web Text))

Max Activating Token Index: 831