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

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

Neuron 2099 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.8880. Min Act: -0.0000

Data Index: 582918 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.9051. Min Act: -0.0000

Data Index: 547173 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.5976. Min Act: -0.0000

Data Index: 488856 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.6500. Min Act: -0.0000

Data Index: 337398 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.4564. Min Act: -0.0000

Data Index: 545709 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.4342. Min Act: -0.0000

Data Index: 1185724 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.5458. Min Act: -0.0000

Data Index: 234003 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.4068. Min Act: -0.0000

Data Index: 464113 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.3717. Min Act: -0.0000

Data Index: 2599 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.4272. Min Act: -0.0000

Data Index: 218334 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.2019. Min Act: -0.0000

Data Index: 276735 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.1543. Min Act: -0.0000

Data Index: 414681 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 2.9051. Min Range: -2.9051

Max Act: 1.9979. Min Act: -0.0000

Data Index: 1141380 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.2076. Min Act: -0.0000

Data Index: 1013920 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.0857. Min Act: -0.0000

Data Index: 184646 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.0712. Min Act: -0.0000

Data Index: 184499 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.1877. Min Act: -0.0000

Data Index: 1016985 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 2.9051. Min Range: -2.9051

Max Act: 1.9695. Min Act: -0.0000

Data Index: 1185170 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.1631. Min Act: -0.0000

Data Index: 1047063 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 2.9051. Min Range: -2.9051

Max Act: 2.1014. Min Act: -0.0000

Data Index: 448764 (C4 (Web Text))

Max Activating Token Index: 460