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

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

Neuron 4716 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.5518. Min Act: -0.0001

Data Index: 1163976 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.4092. Min Act: -0.0001

Data Index: 52812 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.4856. Min Act: -0.0000

Data Index: 454863 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.3361. Min Act: -0.0001

Data Index: 1012470 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.2506. Min Act: -0.0001

Data Index: 852550 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.2101. Min Act: -0.0000

Data Index: 130454 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.3324. Min Act: -0.0001

Data Index: 621563 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1685. Min Act: -0.0001

Data Index: 8937 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1593. Min Act: -0.0001

Data Index: 968623 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1556. Min Act: -0.0001

Data Index: 1274912 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.2194. Min Act: -0.0000

Data Index: 640121 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.0442. Min Act: -0.0001

Data Index: 444212 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.2719. Min Act: -0.0001

Data Index: 336052 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.2222. Min Act: -0.0001

Data Index: 1150197 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1123. Min Act: -0.0000

Data Index: 501511 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.0936. Min Act: -0.0001

Data Index: 560831 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1233796 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1905. Min Act: -0.0000

Data Index: 465416 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.0984. Min Act: -0.0001

Data Index: 284373 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1265. Min Act: -0.0000

Data Index: 624145 (C4 (Web Text))

Max Activating Token Index: 96