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

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

Neuron 4047 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0468. Min Range: -1.0468

Max Act: 1.0468. Min Act: -0.0000

Data Index: 983246 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7805. Min Act: -0.0000

Data Index: 342436 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7601. Min Act: -0.0000

Data Index: 938556 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.6735. Min Act: -0.0000

Data Index: 188334 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.7308. Min Act: -0.0000

Data Index: 179185 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.6678. Min Act: -0.0000

Data Index: 504334 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.6448. Min Act: -0.0000

Data Index: 142618 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.6148. Min Act: -0.0000

Data Index: 650450 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1278252 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.5871. Min Act: -0.0000

Data Index: 414519 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.5634. Min Act: -0.0000

Data Index: 613997 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.5794. Min Act: -0.0000

Data Index: 928938 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.5573. Min Act: -0.0000

Data Index: 354657 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.5732. Min Act: -0.0000

Data Index: 635241 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1231907 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.5632. Min Act: -0.0000

Data Index: 529294 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.5500. Min Act: -0.0000

Data Index: 828149 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.5595. Min Act: -0.0000

Data Index: 989820 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.5662. Min Act: -0.0000

Data Index: 617392 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 1.0468. Min Range: -1.0468

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1169090 (C4 (Web Text))

Max Activating Token Index: 817