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

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

Neuron 653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0898. Min Range: -2.0898

Max Act: 2.0492. Min Act: -0.0000

Data Index: 1331034 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 2.0898. Min Range: -2.0898

Max Act: 2.0898. Min Act: -0.0000

Data Index: 182186 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8977. Min Act: -0.0000

Data Index: 770889 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.8771. Min Act: -0.0000

Data Index: 1085213 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.6764. Min Act: -0.0000

Data Index: 138218 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.6068. Min Act: -0.0000

Data Index: 1158283 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.5313. Min Act: -0.0000

Data Index: 1265714 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.4884. Min Act: -0.0000

Data Index: 431777 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.4852. Min Act: -0.0000

Data Index: 1176563 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.3481. Min Act: -0.0000

Data Index: 629629 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.3819. Min Act: -0.0000

Data Index: 1124397 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.4044. Min Act: -0.0000

Data Index: 1091072 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.4072. Min Act: -0.0000

Data Index: 99323 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.3555. Min Act: -0.0000

Data Index: 1320321 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.3602. Min Act: -0.0000

Data Index: 688129 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.4224. Min Act: -0.0000

Data Index: 712561 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.3319. Min Act: -0.0000

Data Index: 629789 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.3716. Min Act: -0.0000

Data Index: 507375 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.3048. Min Act: -0.0000

Data Index: 703993 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.3508. Min Act: -0.0000

Data Index: 516453 (C4 (Web Text))

Max Activating Token Index: 944