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

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

Neuron 1678 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0971. Min Act: -0.0003

Data Index: 1246190 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0933. Min Act: -0.0003

Data Index: 1020458 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0905. Min Act: -0.0004

Data Index: 123135 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0938. Min Act: -0.0003

Data Index: 1184607 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0883. Min Act: -0.0003

Data Index: 790785 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0891. Min Act: -0.0003

Data Index: 728037 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0815. Min Act: -0.0002

Data Index: 939300 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0877. Min Act: -0.0003

Data Index: 334652 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0855. Min Act: -0.0003

Data Index: 518079 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0828. Min Act: -0.0003

Data Index: 402309 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0863. Min Act: -0.0004

Data Index: 1138921 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0810. Min Act: -0.0003

Data Index: 955251 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0831. Min Act: -0.0004

Data Index: 393003 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0818. Min Act: -0.0002

Data Index: 419096 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0789. Min Act: -0.0003

Data Index: 1058599 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0791. Min Act: -0.0003

Data Index: 934785 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0830. Min Act: -0.0004

Data Index: 458325 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0755. Min Act: -0.0003

Data Index: 643838 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0769. Min Act: -0.0003

Data Index: 326965 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1133738 (C4 (Web Text))

Max Activating Token Index: 669