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

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

Neuron 2516 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1171. Min Act: -0.0000

Data Index: 842984 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1172. Min Act: -0.0000

Data Index: 760808 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1254971 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1143. Min Act: -0.0000

Data Index: 538132 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1087. Min Act: -0.0000

Data Index: 483450 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1139370 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1221862 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1064. Min Act: -0.0000

Data Index: 588173 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1042. Min Act: -0.0000

Data Index: 383855 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1055. Min Act: -0.0000

Data Index: 146216 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1017. Min Act: -0.0000

Data Index: 329721 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1010. Min Act: -0.0000

Data Index: 88123 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1234441 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1089717 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0993. Min Act: -0.0000

Data Index: 927965 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0959. Min Act: -0.0000

Data Index: 368153 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1043307 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1123873 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1008930 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0997. Min Act: -0.0001

Data Index: 370320 (C4 (Web Text))

Max Activating Token Index: 994