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

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

Neuron 4728 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: 2.1959. Min Range: -2.1959

Max Act: 2.1959. Min Act: -0.0000

Data Index: 1251570 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.9110. Min Act: -0.0000

Data Index: 545618 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.8096. Min Act: -0.0000

Data Index: 945810 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.7805. Min Act: -0.0000

Data Index: 81715 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.8712. Min Act: -0.0000

Data Index: 50989 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.7612. Min Act: -0.0000

Data Index: 517835 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.6626. Min Act: -0.0000

Data Index: 878586 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.7806. Min Act: -0.0000

Data Index: 1245263 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.7565. Min Act: -0.0000

Data Index: 822496 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.7345. Min Act: -0.0000

Data Index: 1099855 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.7374. Min Act: -0.0000

Data Index: 367606 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.7125. Min Act: -0.0000

Data Index: 749690 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.6154. Min Act: -0.0000

Data Index: 796059 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.7118. Min Act: -0.0000

Data Index: 62980 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.6194. Min Act: -0.0000

Data Index: 995694 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.6801. Min Act: -0.0000

Data Index: 1296734 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.5736. Min Act: -0.0000

Data Index: 403125 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.5625. Min Act: -0.0000

Data Index: 266584 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.6593. Min Act: -0.0000

Data Index: 4576 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 2.1959. Min Range: -2.1959

Max Act: 1.6511. Min Act: -0.0000

Data Index: 1314146 (C4 (Web Text))

Max Activating Token Index: 333