Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2568 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2306. Min Act: -0.0003

Data Index: 60956 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2043. Min Act: -0.0003

Data Index: 513648 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2254. Min Act: -0.0003

Data Index: 28975 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2071. Min Act: -0.0003

Data Index: 1189474 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2141. Min Act: -0.0003

Data Index: 1042138 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2045. Min Act: -0.0003

Data Index: 560055 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2067. Min Act: -0.0003

Data Index: 321050 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2134. Min Act: -0.0003

Data Index: 487911 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2111. Min Act: -0.0003

Data Index: 813789 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2120. Min Act: -0.0003

Data Index: 1106959 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2004. Min Act: -0.0003

Data Index: 143 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1999. Min Act: -0.0003

Data Index: 1262905 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2139. Min Act: -0.0003

Data Index: 1034388 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1993. Min Act: -0.0003

Data Index: 438604 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2144. Min Act: -0.0003

Data Index: 56741 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2066. Min Act: -0.0003

Data Index: 522086 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2005. Min Act: -0.0003

Data Index: 821280 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1988. Min Act: -0.0003

Data Index: 49823 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2058. Min Act: -0.0003

Data Index: 474759 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1904. Min Act: -0.0003

Data Index: 1145782 (C4 (Web Text))

Max Activating Token Index: 781