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

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

Neuron 1944 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: 0.0862. Min Range: -0.0862

Max Act: 0.0862. Min Act: -0.0005

Data Index: 988503 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0838. Min Act: -0.0005

Data Index: 610172 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0852. Min Act: -0.0005

Data Index: 728565 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0812. Min Act: -0.0005

Data Index: 1060141 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0784. Min Act: -0.0005

Data Index: 819997 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0770. Min Act: -0.0005

Data Index: 970398 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0815. Min Act: -0.0005

Data Index: 225659 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0840. Min Act: -0.0005

Data Index: 804131 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0777. Min Act: -0.0005

Data Index: 1210084 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0768. Min Act: -0.0005

Data Index: 250900 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0760. Min Act: -0.0005

Data Index: 745560 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0727. Min Act: -0.0005

Data Index: 620727 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0764. Min Act: -0.0005

Data Index: 261689 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0747. Min Act: -0.0005

Data Index: 363443 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0756. Min Act: -0.0005

Data Index: 1353923 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0764. Min Act: -0.0005

Data Index: 1526502 (Python Code)

Max Activating Token Index: 897

Text #16

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0784. Min Act: -0.0005

Data Index: 1276524 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0756. Min Act: -0.0005

Data Index: 418744 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0785. Min Act: -0.0005

Data Index: 1349107 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0740. Min Act: -0.0005

Data Index: 405742 (C4 (Web Text))

Max Activating Token Index: 369