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

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

Neuron 3024 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: 0.8773. Min Range: -0.8773

Max Act: 0.8773. Min Act: -0.0000

Data Index: 383435 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.8435. Min Act: -0.0000

Data Index: 917466 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7985. Min Act: -0.0000

Data Index: 1240971 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7098. Min Act: -0.0000

Data Index: 561618 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1324920 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6961. Min Act: -0.0000

Data Index: 781603 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6202. Min Act: -0.0000

Data Index: 81576 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7033. Min Act: -0.0001

Data Index: 945765 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6245. Min Act: -0.0000

Data Index: 55137 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6765. Min Act: -0.0000

Data Index: 36121 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6937. Min Act: -0.0000

Data Index: 527279 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6037. Min Act: -0.0000

Data Index: 868264 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1011130 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1068458 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1138789 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6521. Min Act: -0.0000

Data Index: 478934 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6675. Min Act: -0.0000

Data Index: 163323 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6203. Min Act: -0.0000

Data Index: 217106 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1321622 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1007934 (C4 (Web Text))

Max Activating Token Index: 595