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

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

Neuron 1183 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1110. Min Act: -0.0000

Data Index: 710483 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0995. Min Act: -0.0000

Data Index: 888093 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1186. Min Act: -0.0000

Data Index: 687406 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1076. Min Act: -0.0000

Data Index: 479880 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0973. Min Act: -0.0000

Data Index: 427003 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0962. Min Act: -0.0000

Data Index: 843776 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0984. Min Act: -0.0000

Data Index: 982792 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0950. Min Act: 0.0001

Data Index: 828349 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0941. Min Act: -0.0000

Data Index: 511001 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0890. Min Act: 0.0000

Data Index: 888460 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0884. Min Act: -0.0000

Data Index: 135923 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0796. Min Act: -0.0000

Data Index: 510215 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1045390 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0803. Min Act: -0.0000

Data Index: 386288 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0780. Min Act: 0.0004

Data Index: 731266 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0964. Min Act: -0.0000

Data Index: 535672 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0860. Min Act: 0.0000

Data Index: 610142 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0867. Min Act: 0.0000

Data Index: 1463528 (Python Code)

Max Activating Token Index: 876

Text #18

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1506583 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0871. Min Act: -0.0000

Data Index: 394693 (C4 (Web Text))

Max Activating Token Index: 120