Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3802 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.7652. Min Act: -0.0001

Data Index: 1300718 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.7090. Min Act: -0.0001

Data Index: 1104754 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5824. Min Act: -0.0001

Data Index: 1170433 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5788. Min Act: -0.0001

Data Index: 213108 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6136. Min Act: -0.0001

Data Index: 940502 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6272. Min Act: -0.0001

Data Index: 465137 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5821. Min Act: -0.0001

Data Index: 233086 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5647. Min Act: -0.0001

Data Index: 1012477 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.6059. Min Act: -0.0001

Data Index: 971652 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5776. Min Act: -0.0001

Data Index: 384394 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5637. Min Act: -0.0001

Data Index: 1294156 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5561. Min Act: -0.0001

Data Index: 125891 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5909. Min Act: -0.0001

Data Index: 1328309 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5558. Min Act: -0.0001

Data Index: 473653 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5175. Min Act: -0.0001

Data Index: 948815 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5324. Min Act: -0.0001

Data Index: 642064 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5522. Min Act: -0.0001

Data Index: 970033 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5370. Min Act: -0.0001

Data Index: 174078 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.5063. Min Act: -0.0001

Data Index: 966067 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.7652. Min Range: -0.7652

Max Act: 0.4989. Min Act: -0.0001

Data Index: 377408 (C4 (Web Text))

Max Activating Token Index: 635