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

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

Neuron 3479 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.2349. Min Act: -0.0000

Data Index: 504425 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1827. Min Act: -0.0000

Data Index: 87835 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1091. Min Act: -0.0000

Data Index: 382796 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1276026 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1528354 (Python Code)

Max Activating Token Index: 52

Text #5

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1065. Min Act: -0.0000

Data Index: 792216 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1075790 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1040. Min Act: -0.0000

Data Index: 124595 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1013. Min Act: -0.0000

Data Index: 940341 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1254980 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1355818 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1031. Min Act: -0.0000

Data Index: 695360 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.0995. Min Act: -0.0000

Data Index: 993817 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1336146 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1326701 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.0978. Min Act: -0.0000

Data Index: 83019 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1324560 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1004. Min Act: -0.0000

Data Index: 112953 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1184432 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.0945. Min Act: -0.0000

Data Index: 186223 (C4 (Web Text))

Max Activating Token Index: 43