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

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

Neuron 4748 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1163918 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6972. Min Act: -0.0000

Data Index: 249229 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.6606. Min Act: -0.0000

Data Index: 70106 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5637. Min Act: -0.0000

Data Index: 442146 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1229679 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5750. Min Act: -0.0000

Data Index: 571867 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1042867 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5347. Min Act: -0.0000

Data Index: 733207 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5286. Min Act: -0.0000

Data Index: 759314 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5115. Min Act: -0.0000

Data Index: 135999 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1118979 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.5267. Min Act: -0.0000

Data Index: 738692 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4632. Min Act: -0.0000

Data Index: 98738 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4804. Min Act: -0.0000

Data Index: 960379 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4611. Min Act: -0.0000

Data Index: 442693 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4831. Min Act: -0.0000

Data Index: 953632 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4559. Min Act: -0.0000

Data Index: 703123 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4674. Min Act: -0.0000

Data Index: 812309 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4521. Min Act: -0.0000

Data Index: 529339 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.8823. Min Range: -0.8823

Max Act: 0.4835. Min Act: -0.0000

Data Index: 149549 (C4 (Web Text))

Max Activating Token Index: 540