Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2917 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0748. Min Range: -1.0748

Max Act: 1.0748. Min Act: -0.0000

Data Index: 496708 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9813. Min Act: -0.0000

Data Index: 987177 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9864. Min Act: -0.0000

Data Index: 897071 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9541. Min Act: -0.0001

Data Index: 436987 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9777. Min Act: -0.0000

Data Index: 906346 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9587. Min Act: -0.0000

Data Index: 595330 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9585. Min Act: -0.0001

Data Index: 1300023 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1304486 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.8803. Min Act: -0.0001

Data Index: 1229638 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9210. Min Act: -0.0000

Data Index: 720013 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9193. Min Act: -0.0001

Data Index: 273722 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9159. Min Act: -0.0000

Data Index: 580828 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9167. Min Act: -0.0001

Data Index: 29290 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9117. Min Act: -0.0000

Data Index: 558979 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1212914 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1149971 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.8986. Min Act: -0.0000

Data Index: 73761 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.9300. Min Act: -0.0000

Data Index: 583971 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1181048 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 1.0748. Min Range: -1.0748

Max Act: 0.8641. Min Act: -0.0001

Data Index: 585140 (C4 (Web Text))

Max Activating Token Index: 15