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

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

Neuron 1093 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1081. Min Act: -0.0005

Data Index: 1112383 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0996. Min Act: -0.0005

Data Index: 342793 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1067. Min Act: -0.0005

Data Index: 1157 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1059. Min Act: -0.0005

Data Index: 24985 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1031. Min Act: -0.0005

Data Index: 587838 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1079. Min Act: -0.0005

Data Index: 711298 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1083. Min Act: -0.0005

Data Index: 440185 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1067. Min Act: -0.0005

Data Index: 1153883 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0897. Min Act: -0.0005

Data Index: 613470 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1032. Min Act: -0.0005

Data Index: 206607 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1024. Min Act: -0.0005

Data Index: 433839 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0981. Min Act: -0.0005

Data Index: 222036 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0990. Min Act: -0.0005

Data Index: 808224 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0988. Min Act: -0.0005

Data Index: 994320 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0951. Min Act: -0.0005

Data Index: 1238580 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0957. Min Act: -0.0005

Data Index: 745897 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0977. Min Act: -0.0005

Data Index: 939940 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0901. Min Act: -0.0005

Data Index: 809972 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0992. Min Act: -0.0005

Data Index: 929290 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1120. Min Act: -0.0005

Data Index: 182563 (C4 (Web Text))

Max Activating Token Index: 662