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

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

Neuron 4 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: 0.0083. Min Range: -0.0083

Max Act: 0.0083. Min Act: -0.0006

Data Index: 836726 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0006

Data Index: 484821 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0006

Data Index: 818873 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0005

Data Index: 342819 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0006

Data Index: 814729 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0006

Data Index: 850174 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0006

Data Index: 462459 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1288100 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0071. Min Act: -0.0006

Data Index: 779806 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1219698 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0006

Data Index: 599219 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0006

Data Index: 621609 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1342558 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1195723 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1313407 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0006

Data Index: 244879 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1354425 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0006

Data Index: 852448 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0006

Data Index: 964102 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1347007 (C4 (Web Text))

Max Activating Token Index: 804