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

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

Neuron 1308 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: 0.4851. Min Range: -0.4851

Max Act: 0.4851. Min Act: -0.0000

Data Index: 858652 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4228. Min Act: -0.0000

Data Index: 772555 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4516. Min Act: -0.0000

Data Index: 654470 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4072. Min Act: -0.0000

Data Index: 125786 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4664. Min Act: -0.0000

Data Index: 417905 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4076. Min Act: -0.0000

Data Index: 707980 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3763. Min Act: -0.0000

Data Index: 898871 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4451. Min Act: -0.0000

Data Index: 857485 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1317305 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1151625 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.4513. Min Act: -0.0000

Data Index: 129345 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3820. Min Act: -0.0000

Data Index: 311964 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3808. Min Act: -0.0000

Data Index: 57278 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3828. Min Act: -0.0000

Data Index: 554640 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3243. Min Act: -0.0000

Data Index: 387779 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3692. Min Act: -0.0000

Data Index: 35031 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3680. Min Act: -0.0000

Data Index: 360371 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3719. Min Act: -0.0000

Data Index: 42402 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3702. Min Act: -0.0000

Data Index: 252798 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3385. Min Act: -0.0000

Data Index: 600297 (C4 (Web Text))

Max Activating Token Index: 317