Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 999 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1100. Min Act: -0.0001

Data Index: 925624 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1111. Min Act: -0.0003

Data Index: 1159907 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1138. Min Act: -0.0002

Data Index: 930995 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1075. Min Act: -0.0002

Data Index: 608622 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1011. Min Act: -0.0002

Data Index: 754974 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0996. Min Act: -0.0002

Data Index: 797238 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1358302 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0950. Min Act: -0.0002

Data Index: 83405 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1097774 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0975. Min Act: -0.0002

Data Index: 408690 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1310117 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1076452 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0945. Min Act: -0.0002

Data Index: 568294 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0908. Min Act: -0.0002

Data Index: 533262 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0962. Min Act: -0.0002

Data Index: 381027 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0931. Min Act: -0.0002

Data Index: 416969 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0928. Min Act: -0.0002

Data Index: 708823 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1036527 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1353229 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1106735 (C4 (Web Text))

Max Activating Token Index: 266