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

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

Neuron 72 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5540. Min Act: -0.0001

Data Index: 592482 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4602. Min Act: -0.0001

Data Index: 319106 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4544. Min Act: -0.0001

Data Index: 711868 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4668. Min Act: -0.0000

Data Index: 822840 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4297. Min Act: -0.0001

Data Index: 344411 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1109460 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4235. Min Act: -0.0000

Data Index: 58208 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4169. Min Act: -0.0000

Data Index: 404014 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1357474 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3871. Min Act: -0.0001

Data Index: 442187 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4126. Min Act: -0.0001

Data Index: 272352 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4077. Min Act: -0.0000

Data Index: 558083 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1122402 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3953. Min Act: -0.0000

Data Index: 733791 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3997. Min Act: -0.0000

Data Index: 151103 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3800. Min Act: -0.0001

Data Index: 682571 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3933. Min Act: -0.0001

Data Index: 1133223 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3660. Min Act: -0.0000

Data Index: 335553 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3540. Min Act: -0.0000

Data Index: 454160 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.3886. Min Act: -0.0000

Data Index: 239986 (C4 (Web Text))

Max Activating Token Index: 696