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

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

Neuron 3979 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: 0.8020. Min Range: -0.8020

Max Act: 0.8020. Min Act: -0.0001

Data Index: 845431 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6862. Min Act: -0.0001

Data Index: 459520 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1155243 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1083556 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6299. Min Act: -0.0001

Data Index: 530672 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6346. Min Act: -0.0001

Data Index: 406876 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6086. Min Act: -0.0001

Data Index: 881412 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.5749. Min Act: -0.0001

Data Index: 207024 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6027. Min Act: -0.0001

Data Index: 794692 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6072. Min Act: -0.0001

Data Index: 831450 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6099. Min Act: -0.0001

Data Index: 823129 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.5755. Min Act: -0.0001

Data Index: 1048969 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.5973. Min Act: -0.0001

Data Index: 1185331 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.5718. Min Act: -0.0001

Data Index: 1218514 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1313213 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.5546. Min Act: -0.0001

Data Index: 897811 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.5332. Min Act: -0.0001

Data Index: 213082 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.4841. Min Act: -0.0001

Data Index: 343406 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.5772. Min Act: -0.0001

Data Index: 1195374 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.5629. Min Act: -0.0001

Data Index: 198638 (C4 (Web Text))

Max Activating Token Index: 100