Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2815 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1184857 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2549. Min Act: -0.0000

Data Index: 443236 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1088045 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2239. Min Act: -0.0000

Data Index: 944033 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2194. Min Act: -0.0000

Data Index: 612018 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1330003 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2166. Min Act: -0.0000

Data Index: 115220 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1333209 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2128. Min Act: -0.0000

Data Index: 1076937 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2099. Min Act: -0.0000

Data Index: 405752 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1310066 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.1906. Min Act: -0.0000

Data Index: 186954 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.1973. Min Act: -0.0000

Data Index: 318923 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.1954. Min Act: -0.0000

Data Index: 580678 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2068. Min Act: -0.0000

Data Index: 966765 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.1992. Min Act: -0.0000

Data Index: 898416 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.1932. Min Act: -0.0000

Data Index: 43852 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.1982. Min Act: -0.0000

Data Index: 708978 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1560248 (Python Code)

Max Activating Token Index: 1011

Text #19

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.1912. Min Act: -0.0000

Data Index: 817064 (C4 (Web Text))

Max Activating Token Index: 201