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

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

Neuron 2778 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1167. Min Act: -0.0000

Data Index: 688151 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1151. Min Act: -0.0000

Data Index: 235043 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1102. Min Act: -0.0000

Data Index: 774356 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1175502 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1066. Min Act: -0.0000

Data Index: 50145 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1069674 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1009. Min Act: -0.0000

Data Index: 661174 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1129426 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1072. Min Act: -0.0000

Data Index: 871956 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1052. Min Act: -0.0000

Data Index: 129814 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0978. Min Act: -0.0000

Data Index: 955875 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1015. Min Act: -0.0000

Data Index: 240571 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1095326 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1038. Min Act: -0.0000

Data Index: 666571 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0982. Min Act: -0.0000

Data Index: 975849 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0977. Min Act: -0.0000

Data Index: 601473 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0952. Min Act: -0.0000

Data Index: 596358 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1045. Min Act: -0.0000

Data Index: 710675 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0930. Min Act: -0.0000

Data Index: 689712 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1287511 (C4 (Web Text))

Max Activating Token Index: 646