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

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

Neuron 321 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0005

Data Index: 476523 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0796. Min Act: -0.0005

Data Index: 909095 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0769. Min Act: -0.0005

Data Index: 1419733 (Python Code)

Max Activating Token Index: 220

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0766. Min Act: -0.0005

Data Index: 266937 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0718. Min Act: -0.0005

Data Index: 614815 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0747. Min Act: -0.0005

Data Index: 1023199 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0740. Min Act: -0.0005

Data Index: 1165986 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0718. Min Act: -0.0005

Data Index: 952723 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0724. Min Act: -0.0005

Data Index: 1350147 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0714. Min Act: -0.0005

Data Index: 538807 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0681. Min Act: -0.0005

Data Index: 1580617 (Python Code)

Max Activating Token Index: 384

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0724. Min Act: -0.0005

Data Index: 434633 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0693. Min Act: -0.0005

Data Index: 813230 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0691. Min Act: -0.0005

Data Index: 1127340 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0656. Min Act: -0.0005

Data Index: 1218647 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0683. Min Act: -0.0005

Data Index: 1546721 (Python Code)

Max Activating Token Index: 842

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0655. Min Act: -0.0005

Data Index: 288592 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0670. Min Act: -0.0005

Data Index: 917802 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0694. Min Act: -0.0005

Data Index: 627084 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0676. Min Act: -0.0005

Data Index: 440425 (C4 (Web Text))

Max Activating Token Index: 433