Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1426 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0860. Min Act: -0.0002

Data Index: 366591 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1337116 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0852. Min Act: -0.0002

Data Index: 578649 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0791. Min Act: -0.0002

Data Index: 399287 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0799. Min Act: -0.0002

Data Index: 743735 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0808. Min Act: -0.0001

Data Index: 6734 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0752. Min Act: -0.0001

Data Index: 4605 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1093983 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1090149 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1038840 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1395334 (Python Code)

Max Activating Token Index: 668

Text #11

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0725. Min Act: -0.0002

Data Index: 971798 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0708. Min Act: -0.0001

Data Index: 979147 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0682. Min Act: -0.0002

Data Index: 704675 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0743. Min Act: -0.0001

Data Index: 955998 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0742. Min Act: -0.0002

Data Index: 270748 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1257189 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1196758 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0699. Min Act: -0.0002

Data Index: 609379 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0700. Min Act: -0.0002

Data Index: 63937 (C4 (Web Text))

Max Activating Token Index: 887