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

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

Neuron 4170 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.9963. Min Act: -0.0001

Data Index: 154510 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.9342. Min Act: -0.0001

Data Index: 493065 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.9226. Min Act: -0.0000

Data Index: 768770 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8874. Min Act: -0.0001

Data Index: 441497 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.9044. Min Act: -0.0001

Data Index: 79650 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8996. Min Act: -0.0000

Data Index: 43767 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8724. Min Act: -0.0001

Data Index: 29090 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8902. Min Act: -0.0001

Data Index: 340830 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8413. Min Act: -0.0001

Data Index: 469396 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8195. Min Act: -0.0001

Data Index: 276978 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1034233 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8000. Min Act: -0.0000

Data Index: 986298 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7870. Min Act: -0.0001

Data Index: 1309180 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1099733 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8152. Min Act: -0.0001

Data Index: 731430 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7892. Min Act: -0.0001

Data Index: 1169880 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7860. Min Act: -0.0001

Data Index: 763274 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7788. Min Act: -0.0001

Data Index: 406287 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1148287 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8204. Min Act: -0.0001

Data Index: 1282813 (C4 (Web Text))

Max Activating Token Index: 223