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

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

Neuron 2039 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: 0.0091. Min Range: -0.0091

Max Act: 0.0091. Min Act: -0.0006

Data Index: 56222 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0090. Min Act: -0.0006

Data Index: 365265 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0087. Min Act: -0.0005

Data Index: 866721 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1136427 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1264306 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0078. Min Act: -0.0006

Data Index: 374394 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0081. Min Act: -0.0006

Data Index: 813787 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0077. Min Act: -0.0006

Data Index: 146544 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0080. Min Act: -0.0006

Data Index: 806365 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0076. Min Act: -0.0006

Data Index: 315453 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1096665 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0075. Min Act: -0.0006

Data Index: 697332 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1110773 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1164074 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1316809 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1028971 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0073. Min Act: -0.0006

Data Index: 816895 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0073. Min Act: -0.0006

Data Index: 1289380 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0071. Min Act: -0.0006

Data Index: 596694 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1002120 (C4 (Web Text))

Max Activating Token Index: 596