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

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

Neuron 1454 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: 0.0077. Min Range: -0.0077

Max Act: 0.0077. Min Act: -0.0006

Data Index: 139503 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0073. Min Act: -0.0006

Data Index: 767466 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0074. Min Act: -0.0006

Data Index: 997378 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0074. Min Act: -0.0005

Data Index: 456675 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0073. Min Act: -0.0006

Data Index: 623192 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0075. Min Act: -0.0006

Data Index: 383141 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0072. Min Act: -0.0006

Data Index: 218425 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0071. Min Act: -0.0006

Data Index: 832466 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1112715 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0006

Data Index: 631242 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1286672 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1230897 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0069. Min Act: -0.0006

Data Index: 559053 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0006

Data Index: 843912 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0006

Data Index: 746653 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0005

Data Index: 1008279 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1163918 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0005

Data Index: 829789 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1159932 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0006

Data Index: 27145 (C4 (Web Text))

Max Activating Token Index: 316