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

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

Neuron 3628 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4267. Min Range: -4.4267

Max Act: 4.4267. Min Act: -0.0000

Data Index: 276877 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 4.4267. Min Range: -4.4267

Max Act: 4.3479. Min Act: -0.0000

Data Index: 114614 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 4.4267. Min Range: -4.4267

Max Act: 4.1401. Min Act: -0.0000

Data Index: 1230518 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.8395. Min Act: -0.0000

Data Index: 406694 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.9890. Min Act: -0.0000

Data Index: 1258920 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.7635. Min Act: -0.0000

Data Index: 971563 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.7339. Min Act: -0.0000

Data Index: 895837 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.7212. Min Act: -0.0000

Data Index: 1160872 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.4480. Min Act: -0.0000

Data Index: 791956 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.4261. Min Act: -0.0001

Data Index: 700253 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.6146. Min Act: -0.0000

Data Index: 931460 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.5843. Min Act: -0.0000

Data Index: 385305 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.2303. Min Act: -0.0000

Data Index: 698728 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.5229. Min Act: -0.0000

Data Index: 382200 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.3567. Min Act: -0.0000

Data Index: 357070 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.6605. Min Act: -0.0000

Data Index: 253222 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.4271. Min Act: -0.0000

Data Index: 847553 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.6250. Min Act: -0.0000

Data Index: 333074 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.4697. Min Act: -0.0000

Data Index: 1115417 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 4.4267. Min Range: -4.4267

Max Act: 3.4743. Min Act: -0.0000

Data Index: 1176654 (C4 (Web Text))

Max Activating Token Index: 170