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

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

Neuron 1898 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.7524. Min Act: -0.0000

Data Index: 461378 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.4564. Min Act: -0.0000

Data Index: 286113 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.5808. Min Act: -0.0000

Data Index: 925445 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.4965. Min Act: -0.0000

Data Index: 514503 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3973. Min Act: -0.0000

Data Index: 555765 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.2627. Min Act: -0.0000

Data Index: 1118512 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.4524. Min Act: -0.0000

Data Index: 820393 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3483. Min Act: -0.0000

Data Index: 529636 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3397. Min Act: -0.0000

Data Index: 554972 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.5304. Min Act: -0.0000

Data Index: 841144 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.2151. Min Act: -0.0000

Data Index: 541549 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.1848. Min Act: -0.0000

Data Index: 462864 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3153. Min Act: -0.0000

Data Index: 1437041 (Python Code)

Max Activating Token Index: 176

Text #13

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.1652. Min Act: -0.0000

Data Index: 1291874 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.1823. Min Act: -0.0000

Data Index: 551978 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.1891. Min Act: -0.0000

Data Index: 257886 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.2052. Min Act: -0.0000

Data Index: 110443 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.1428. Min Act: -0.0000

Data Index: 416166 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.0878. Min Act: -0.0000

Data Index: 545657 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.0834. Min Act: -0.0000

Data Index: 335835 (C4 (Web Text))

Max Activating Token Index: 149