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

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

Neuron 453 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.7708. Min Act: -0.0001

Data Index: 687289 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1276944 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1316467 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6959. Min Act: -0.0001

Data Index: 933213 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6865. Min Act: -0.0000

Data Index: 556497 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6897. Min Act: -0.0001

Data Index: 54915 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6675. Min Act: -0.0001

Data Index: 349984 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6495. Min Act: -0.0001

Data Index: 99617 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.7006. Min Act: -0.0001

Data Index: 107130 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6414. Min Act: -0.0001

Data Index: 85115 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6745. Min Act: -0.0001

Data Index: 854987 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1137508 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6660. Min Act: -0.0001

Data Index: 653507 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6191. Min Act: -0.0001

Data Index: 155974 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6339. Min Act: -0.0001

Data Index: 159481 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6194. Min Act: -0.0000

Data Index: 214453 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6154. Min Act: -0.0001

Data Index: 554765 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6201. Min Act: -0.0000

Data Index: 432387 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6153. Min Act: -0.0001

Data Index: 373003 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5680. Min Act: -0.0000

Data Index: 798290 (C4 (Web Text))

Max Activating Token Index: 135