Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2050 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7811. Min Act: -0.0001

Data Index: 1087124 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7302. Min Act: -0.0001

Data Index: 68934 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7496. Min Act: -0.0001

Data Index: 1106484 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7280. Min Act: -0.0001

Data Index: 862435 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6892. Min Act: -0.0001

Data Index: 894740 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7311. Min Act: -0.0001

Data Index: 906933 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6983. Min Act: -0.0001

Data Index: 744519 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6630. Min Act: -0.0001

Data Index: 1075651 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6753. Min Act: -0.0000

Data Index: 250710 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7165. Min Act: -0.0001

Data Index: 749307 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6408. Min Act: -0.0001

Data Index: 1353405 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6964. Min Act: -0.0001

Data Index: 327991 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6492. Min Act: -0.0000

Data Index: 3847 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6714. Min Act: -0.0000

Data Index: 70942 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6534. Min Act: -0.0001

Data Index: 402765 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6290. Min Act: -0.0000

Data Index: 101355 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6502. Min Act: -0.0001

Data Index: 172204 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6473. Min Act: -0.0000

Data Index: 487697 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6461. Min Act: -0.0000

Data Index: 923000 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6132. Min Act: -0.0000

Data Index: 439090 (C4 (Web Text))

Max Activating Token Index: 551