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

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

Neuron 1922 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: 0.0882. Min Range: -0.0882

Max Act: 0.0882. Min Act: -0.0002

Data Index: 407874 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1194164 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0760. Min Act: -0.0001

Data Index: 281892 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1189952 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0708. Min Act: -0.0002

Data Index: 76330 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0729. Min Act: -0.0002

Data Index: 364906 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0715. Min Act: -0.0002

Data Index: 615933 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0695. Min Act: -0.0002

Data Index: 424629 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0704. Min Act: -0.0002

Data Index: 643269 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0683. Min Act: -0.0002

Data Index: 183670 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1161205 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0697. Min Act: -0.0002

Data Index: 2693 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1284290 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1227074 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0702. Min Act: -0.0001

Data Index: 499654 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0675. Min Act: -0.0002

Data Index: 269656 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1283182 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0660. Min Act: -0.0002

Data Index: 685658 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0682. Min Act: -0.0001

Data Index: 138186 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0696. Min Act: -0.0001

Data Index: 562957 (C4 (Web Text))

Max Activating Token Index: 832