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

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

Neuron 1542 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: 0.9585. Min Range: -0.9585

Max Act: 0.8854. Min Act: -0.0001

Data Index: 484016 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.8447. Min Act: -0.0002

Data Index: 112755 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.7205. Min Act: -0.0001

Data Index: 1070860 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.9585. Min Act: -0.0001

Data Index: 970128 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.7643. Min Act: -0.0002

Data Index: 901687 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.7770. Min Act: -0.0001

Data Index: 439980 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.8016. Min Act: -0.0002

Data Index: 1171393 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.8411. Min Act: -0.0002

Data Index: 1045393 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.8681. Min Act: -0.0001

Data Index: 746528 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.8131. Min Act: -0.0001

Data Index: 1210360 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.8677. Min Act: -0.0001

Data Index: 884294 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.8931. Min Act: -0.0002

Data Index: 706381 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.7760. Min Act: -0.0002

Data Index: 1196185 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.8471. Min Act: -0.0002

Data Index: 57812 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.9254. Min Act: -0.0002

Data Index: 528276 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.8177. Min Act: -0.0002

Data Index: 20038 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.7941. Min Act: -0.0002

Data Index: 267047 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.7518. Min Act: -0.0002

Data Index: 1102051 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.7729. Min Act: -0.0001

Data Index: 887 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.9585. Min Range: -0.9585

Max Act: 0.8021. Min Act: -0.0002

Data Index: 1272390 (C4 (Web Text))

Max Activating Token Index: 694