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

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

Neuron 3750 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.3092. Min Act: -0.0002

Data Index: 538107 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.2331. Min Act: -0.0003

Data Index: 1115411 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.2229. Min Act: -0.0003

Data Index: 1305524 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.2196. Min Act: -0.0003

Data Index: 1211264 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.2172. Min Act: -0.0003

Data Index: 716026 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.2143. Min Act: -0.0002

Data Index: 842802 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.2107. Min Act: -0.0003

Data Index: 1253035 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.2073. Min Act: -0.0002

Data Index: 46713 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.2067. Min Act: -0.0002

Data Index: 287379 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.2043. Min Act: -0.0003

Data Index: 963372 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.2023. Min Act: -0.0003

Data Index: 847307 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.2018. Min Act: -0.0003

Data Index: 148738 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.1945. Min Act: -0.0003

Data Index: 755630 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.1917. Min Act: -0.0003

Data Index: 1150611 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.1880. Min Act: -0.0003

Data Index: 465530 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.1873. Min Act: -0.0003

Data Index: 1184046 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.1871. Min Act: -0.0002

Data Index: 1111673 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.1869. Min Act: -0.0002

Data Index: 1056883 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.1846. Min Act: -0.0003

Data Index: 175717 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.3092. Min Range: -0.3092

Max Act: 0.1842. Min Act: -0.0003

Data Index: 1217400 (C4 (Web Text))

Max Activating Token Index: 150