Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4790 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1131765 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.7017. Min Act: -0.0000

Data Index: 31523 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.6717. Min Act: -0.0000

Data Index: 950820 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.6544. Min Act: -0.0000

Data Index: 611702 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.6003. Min Act: -0.0000

Data Index: 84436 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5812. Min Act: -0.0000

Data Index: 44436 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1203425 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.4800. Min Act: -0.0000

Data Index: 333740 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5129. Min Act: -0.0000

Data Index: 722827 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5077. Min Act: -0.0000

Data Index: 284587 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1267383 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1035018 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.4949. Min Act: -0.0000

Data Index: 428110 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1198417 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1204027 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1009824 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1752 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.4397. Min Act: -0.0000

Data Index: 806181 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1174675 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.4430. Min Act: -0.0000

Data Index: 1194380 (C4 (Web Text))

Max Activating Token Index: 747