Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4987 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0002

Data Index: 112952 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1046. Min Act: -0.0002

Data Index: 697205 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1012. Min Act: -0.0003

Data Index: 560339 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0968. Min Act: -0.0003

Data Index: 625790 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0958. Min Act: -0.0003

Data Index: 1255791 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1305529 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0822. Min Act: -0.0002

Data Index: 5914 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0777. Min Act: -0.0003

Data Index: 1112042 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0720. Min Act: -0.0002

Data Index: 460050 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0704. Min Act: -0.0003

Data Index: 760712 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0668. Min Act: -0.0003

Data Index: 845228 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0661. Min Act: -0.0003

Data Index: 1226616 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0647. Min Act: -0.0003

Data Index: 146745 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1045980 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0623. Min Act: -0.0002

Data Index: 149581 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0606. Min Act: -0.0002

Data Index: 358144 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0621. Min Act: -0.0002

Data Index: 354057 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0617. Min Act: -0.0002

Data Index: 574276 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0590. Min Act: -0.0002

Data Index: 499996 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0585. Min Act: -0.0002

Data Index: 821756 (C4 (Web Text))

Max Activating Token Index: 542