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

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

Neuron 3699 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.9824. Min Act: -0.0000

Data Index: 652647 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.4554. Min Act: -0.0000

Data Index: 285956 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.6655. Min Act: -0.0000

Data Index: 514106 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.7762. Min Act: -0.0000

Data Index: 966739 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.6878. Min Act: -0.0000

Data Index: 217622 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.6334. Min Act: -0.0000

Data Index: 1027317 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.8150. Min Act: -0.0000

Data Index: 764845 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.6300. Min Act: -0.0000

Data Index: 1142607 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.4441. Min Act: -0.0000

Data Index: 395405 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.5657. Min Act: -0.0000

Data Index: 967724 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.2769. Min Act: -0.0000

Data Index: 22398 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.6245. Min Act: -0.0000

Data Index: 229337 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.4286. Min Act: -0.0000

Data Index: 325061 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.4102. Min Act: -0.0000

Data Index: 1112675 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.2282. Min Act: -0.0000

Data Index: 571860 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.2188. Min Act: -0.0000

Data Index: 1296064 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.7444. Min Act: -0.0000

Data Index: 771201 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.1760. Min Act: -0.0000

Data Index: 672029 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.3135. Min Act: -0.0000

Data Index: 714190 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 4.9824. Min Range: -4.9824

Max Act: 4.1570. Min Act: -0.0000

Data Index: 163341 (C4 (Web Text))

Max Activating Token Index: 377