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

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

Neuron 4075 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: 0.2997. Min Range: -0.2997

Max Act: 0.2997. Min Act: -0.0001

Data Index: 188247 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2530. Min Act: -0.0000

Data Index: 291848 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2277. Min Act: -0.0000

Data Index: 798239 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2370. Min Act: -0.0000

Data Index: 602355 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2231. Min Act: -0.0001

Data Index: 1038612 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2089. Min Act: -0.0001

Data Index: 396342 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2027. Min Act: -0.0000

Data Index: 85552 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1274535 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.2066. Min Act: -0.0001

Data Index: 731993 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.1918. Min Act: -0.0001

Data Index: 330791 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.1915. Min Act: -0.0000

Data Index: 126162 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1005601 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.1767. Min Act: -0.0000

Data Index: 454199 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.1925. Min Act: -0.0001

Data Index: 844592 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1308346 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.1746. Min Act: -0.0000

Data Index: 903833 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.1706. Min Act: -0.0001

Data Index: 1079561 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.1707. Min Act: -0.0001

Data Index: 288102 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.1634. Min Act: -0.0001

Data Index: 682008 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.2997. Min Range: -0.2997

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1105029 (C4 (Web Text))

Max Activating Token Index: 574