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

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

Neuron 3571 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3567. Min Range: -2.3567

Max Act: 2.3567. Min Act: -0.0000

Data Index: 462706 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 2.3567. Min Range: -2.3567

Max Act: 2.1327. Min Act: -0.0000

Data Index: 787024 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 2.3567. Min Range: -2.3567

Max Act: 2.0386. Min Act: -0.0000

Data Index: 748894 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 2.3567. Min Range: -2.3567

Max Act: 2.0193. Min Act: -0.0000

Data Index: 1203079 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.8830. Min Act: -0.0000

Data Index: 877333 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.8418. Min Act: -0.0000

Data Index: 43507 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.8361. Min Act: -0.0000

Data Index: 206608 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.6738. Min Act: 0.0000

Data Index: 1223360 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.7568. Min Act: 0.0000

Data Index: 477801 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.7511. Min Act: 0.0000

Data Index: 239435 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.6284. Min Act: 0.0000

Data Index: 563362 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.6618. Min Act: -0.0000

Data Index: 1178271 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.6555. Min Act: -0.0000

Data Index: 365401 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.6475. Min Act: 0.0000

Data Index: 1114666 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.5441. Min Act: 0.0000

Data Index: 924493 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.7336. Min Act: 0.0000

Data Index: 1220448 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.7274. Min Act: 0.0000

Data Index: 477627 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.5387. Min Act: -0.0000

Data Index: 306695 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.6260. Min Act: -0.0000

Data Index: 301914 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 2.3567. Min Range: -2.3567

Max Act: 1.6205. Min Act: 0.0000

Data Index: 1002128 (C4 (Web Text))

Max Activating Token Index: 107