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

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

Neuron 3438 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: 0.8642. Min Range: -0.8642

Max Act: 0.8642. Min Act: -0.0000

Data Index: 38197 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8556. Min Act: -0.0000

Data Index: 917020 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1216672 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8341. Min Act: -0.0000

Data Index: 646661 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1086812 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8168. Min Act: -0.0000

Data Index: 938502 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7470. Min Act: -0.0000

Data Index: 203085 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7291. Min Act: -0.0000

Data Index: 134000 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1272169 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6806. Min Act: -0.0000

Data Index: 618840 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6948. Min Act: -0.0000

Data Index: 781434 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7169. Min Act: -0.0000

Data Index: 713807 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7143. Min Act: 0.0001

Data Index: 322047 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6899. Min Act: -0.0000

Data Index: 518955 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7052. Min Act: -0.0000

Data Index: 901922 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6850. Min Act: -0.0000

Data Index: 857865 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6879. Min Act: -0.0000

Data Index: 127900 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6376. Min Act: -0.0000

Data Index: 778943 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6023. Min Act: -0.0000

Data Index: 483799 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6451. Min Act: -0.0000

Data Index: 772269 (C4 (Web Text))

Max Activating Token Index: 356