Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 697 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1259. Min Act: -0.0002

Data Index: 1023356 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1187. Min Act: -0.0002

Data Index: 613617 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1138. Min Act: -0.0002

Data Index: 630000 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1140. Min Act: -0.0002

Data Index: 1029404 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1183. Min Act: -0.0002

Data Index: 252664 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1121. Min Act: -0.0002

Data Index: 238850 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1074. Min Act: -0.0001

Data Index: 762328 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1083. Min Act: -0.0002

Data Index: 537537 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1072. Min Act: -0.0002

Data Index: 1151327 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1098. Min Act: -0.0001

Data Index: 67295 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1053. Min Act: -0.0002

Data Index: 724192 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1321144 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1078. Min Act: -0.0002

Data Index: 111290 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1052. Min Act: -0.0002

Data Index: 384758 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1042. Min Act: -0.0002

Data Index: 297417 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1037. Min Act: -0.0002

Data Index: 661039 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1040. Min Act: -0.0002

Data Index: 21894 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0998. Min Act: -0.0002

Data Index: 1149198 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1017. Min Act: -0.0002

Data Index: 1190576 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1246473 (C4 (Web Text))

Max Activating Token Index: 326