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

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

Neuron 221 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: 1.2099. Min Range: -1.2099

Max Act: 1.2099. Min Act: -0.0000

Data Index: 546231 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 1.2099. Min Range: -1.2099

Max Act: 1.1016. Min Act: -0.0000

Data Index: 837321 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1340477 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1221977 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.8920. Min Act: -0.0000

Data Index: 276907 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.8543. Min Act: -0.0000

Data Index: 204242 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.7878. Min Act: -0.0001

Data Index: 1262377 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1104326 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1055009 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1188572 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.8298. Min Act: -0.0000

Data Index: 445462 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.7218. Min Act: -0.0000

Data Index: 333605 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1070141 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1123813 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.7667. Min Act: -0.0000

Data Index: 624795 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.7604. Min Act: -0.0000

Data Index: 570800 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.7225. Min Act: -0.0000

Data Index: 821258 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.7405. Min Act: -0.0000

Data Index: 67535 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.7331. Min Act: -0.0000

Data Index: 908461 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 1.2099. Min Range: -1.2099

Max Act: 0.7055. Min Act: -0.0000

Data Index: 592539 (C4 (Web Text))

Max Activating Token Index: 726