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

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

Neuron 307 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1208. Min Act: -0.0006

Data Index: 1008783 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1246. Min Act: -0.0006

Data Index: 672521 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1147. Min Act: -0.0006

Data Index: 1333431 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0972. Min Act: -0.0006

Data Index: 773491 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1140. Min Act: -0.0006

Data Index: 163239 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1138. Min Act: -0.0006

Data Index: 1310572 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1147. Min Act: -0.0006

Data Index: 989029 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1023. Min Act: -0.0006

Data Index: 440357 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1051. Min Act: -0.0006

Data Index: 36047 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1093. Min Act: -0.0006

Data Index: 89427 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1038. Min Act: -0.0006

Data Index: 397089 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1034. Min Act: -0.0006

Data Index: 960003 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1064. Min Act: -0.0006

Data Index: 357965 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0983. Min Act: -0.0006

Data Index: 7240 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0978. Min Act: -0.0006

Data Index: 1060842 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1053. Min Act: -0.0006

Data Index: 24578 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0968. Min Act: -0.0006

Data Index: 296765 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0964. Min Act: -0.0006

Data Index: 353632 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1038. Min Act: -0.0006

Data Index: 198857 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1028. Min Act: -0.0006

Data Index: 825709 (C4 (Web Text))

Max Activating Token Index: 671