Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 448 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1030370 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0052. Min Act: -0.0006

Data Index: 737605 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0051. Min Act: -0.0005

Data Index: 554485 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0006

Data Index: 342134 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1065858 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1122470 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0006

Data Index: 509302 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0006

Data Index: 931197 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0006

Data Index: 62722 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0006

Data Index: 1234502 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0006

Data Index: 5511 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0006

Data Index: 1175622 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0006

Data Index: 38721 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0005

Data Index: 1151274 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0006

Data Index: 951105 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0006

Data Index: 31141 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0006

Data Index: 299231 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1313190 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0006

Data Index: 924659 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0006

Data Index: 640657 (C4 (Web Text))

Max Activating Token Index: 1023