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

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

Neuron 3520 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1199. Min Act: -0.0002

Data Index: 1318080 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1223. Min Act: -0.0002

Data Index: 603351 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1152. Min Act: -0.0002

Data Index: 1161808 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1176311 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1091. Min Act: -0.0002

Data Index: 661811 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1088247 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1022. Min Act: -0.0002

Data Index: 558728 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1011. Min Act: -0.0002

Data Index: 735255 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1080. Min Act: -0.0002

Data Index: 323926 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1077801 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1299973 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0910. Min Act: -0.0002

Data Index: 397779 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0942. Min Act: -0.0002

Data Index: 298960 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0975. Min Act: -0.0002

Data Index: 669830 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0935. Min Act: -0.0002

Data Index: 180784 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0937. Min Act: -0.0002

Data Index: 308529 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1240105 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0929. Min Act: -0.0002

Data Index: 66793 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1334044 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0903. Min Act: -0.0002

Data Index: 37140 (C4 (Web Text))

Max Activating Token Index: 514