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

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

Neuron 1629 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: 3.7216. Min Range: -3.7216

Max Act: 3.7216. Min Act: -0.0000

Data Index: 149569 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 3.7216. Min Range: -3.7216

Max Act: 3.2210. Min Act: -0.0000

Data Index: 335055 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.5989. Min Act: -0.0000

Data Index: 1378432 (Python Code)

Max Activating Token Index: 930

Text #3

Max Range: 3.7216. Min Range: -3.7216

Max Act: 3.0072. Min Act: -0.0000

Data Index: 1249268 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.3940. Min Act: -0.0000

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.7261. Min Act: -0.0000

Data Index: 655590 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.9572. Min Act: -0.0000

Data Index: 175197 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.7669. Min Act: -0.0000

Data Index: 1434429 (Python Code)

Max Activating Token Index: 184

Text #8

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.7513. Min Act: -0.0000

Data Index: 449291 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.4913. Min Act: -0.0000

Data Index: 937190 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.7201. Min Act: -0.0000

Data Index: 1018814 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.4457. Min Act: -0.0000

Data Index: 1237876 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.8270. Min Act: -0.0000

Data Index: 206944 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.7607. Min Act: -0.0000

Data Index: 1146692 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.5801. Min Act: -0.0000

Data Index: 786880 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.5660. Min Act: -0.0000

Data Index: 333008 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.3180. Min Act: -0.0000

Data Index: 592554 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.7823. Min Act: -0.0000

Data Index: 50160 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.6417. Min Act: -0.0000

Data Index: 128570 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 3.7216. Min Range: -3.7216

Max Act: 2.1550. Min Act: -0.0000

Data Index: 1325135 (C4 (Web Text))

Max Activating Token Index: 136