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

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

Neuron 3581 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1201692 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1014972 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1032. Min Act: -0.0001

Data Index: 676893 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1008. Min Act: -0.0001

Data Index: 349244 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1044. Min Act: -0.0001

Data Index: 103661 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1008. Min Act: -0.0001

Data Index: 506063 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0988. Min Act: -0.0001

Data Index: 688134 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0988. Min Act: -0.0001

Data Index: 136418 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0951. Min Act: -0.0001

Data Index: 693000 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0931. Min Act: -0.0001

Data Index: 951146 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1032217 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0953. Min Act: -0.0001

Data Index: 584076 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0959. Min Act: -0.0001

Data Index: 462074 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0922. Min Act: -0.0001

Data Index: 965110 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0920. Min Act: -0.0001

Data Index: 906227 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0916. Min Act: -0.0001

Data Index: 651519 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0945. Min Act: -0.0001

Data Index: 428505 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0940. Min Act: -0.0001

Data Index: 479820 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0973. Min Act: -0.0001

Data Index: 410916 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1055816 (C4 (Web Text))

Max Activating Token Index: 658