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

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

Neuron 1027 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: 0.0058. Min Range: -0.0058

Max Act: 0.0057. Min Act: -0.0006

Data Index: 603863 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0058. Min Act: -0.0006

Data Index: 20107 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0055. Min Act: -0.0006

Data Index: 332624 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0056. Min Act: -0.0006

Data Index: 39472 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0056. Min Act: -0.0006

Data Index: 406177 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1266385 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0055. Min Act: -0.0006

Data Index: 1159034 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0053. Min Act: -0.0006

Data Index: 829900 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0054. Min Act: -0.0006

Data Index: 129523 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0052. Min Act: -0.0006

Data Index: 662191 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1340365 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0052. Min Act: -0.0006

Data Index: 321000 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0049. Min Act: -0.0006

Data Index: 513594 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0049. Min Act: -0.0006

Data Index: 386710 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0048. Min Act: -0.0006

Data Index: 672742 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0048. Min Act: -0.0006

Data Index: 1096691 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0046. Min Act: -0.0006

Data Index: 665068 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0046. Min Act: -0.0005

Data Index: 1442458 (Python Code)

Max Activating Token Index: 671

Text #18

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0046. Min Act: -0.0006

Data Index: 312135 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0045. Min Act: -0.0006

Data Index: 1097564 (C4 (Web Text))

Max Activating Token Index: 32