Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2720 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8771. Min Act: -0.0001

Data Index: 888611 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.7939. Min Act: -0.0000

Data Index: 242749 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1112555 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.6324. Min Act: -0.0000

Data Index: 465446 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1299907 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.6374. Min Act: -0.0000

Data Index: 888182 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.6259. Min Act: -0.0000

Data Index: 65871 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1074491 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.6028. Min Act: -0.0000

Data Index: 479991 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.6937. Min Act: -0.0000

Data Index: 936807 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.5981. Min Act: -0.0000

Data Index: 222050 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1296978 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.5675. Min Act: -0.0000

Data Index: 130209 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1256558 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.5832. Min Act: -0.0000

Data Index: 795119 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1213588 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.5648. Min Act: -0.0000

Data Index: 796111 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.5673. Min Act: -0.0000

Data Index: 800585 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.6036. Min Act: -0.0000

Data Index: 988734 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1068972 (C4 (Web Text))

Max Activating Token Index: 427