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

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

Neuron 2649 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.8378. Min Act: -0.0000

Data Index: 1302778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.6650. Min Act: -0.0000

Data Index: 609553 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.6453. Min Act: -0.0000

Data Index: 1287068 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.4950. Min Act: -0.0000

Data Index: 747583 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.6480. Min Act: -0.0000

Data Index: 690027 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.3358. Min Act: -0.0000

Data Index: 939291 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.3291. Min Act: -0.0000

Data Index: 436783 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.3234. Min Act: -0.0000

Data Index: 245598 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.4102. Min Act: -0.0000

Data Index: 152812 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.2126. Min Act: -0.0000

Data Index: 8050 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.1953. Min Act: -0.0000

Data Index: 919976 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.0727. Min Act: -0.0000

Data Index: 1200503 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.0448. Min Act: -0.0000

Data Index: 401000 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.1453. Min Act: -0.0000

Data Index: 711390 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.2533. Min Act: -0.0000

Data Index: 879014 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.1142. Min Act: -0.0000

Data Index: 654965 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.2212. Min Act: -0.0000

Data Index: 189626 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 2.8378. Min Range: -2.8378

Max Act: 1.9731. Min Act: -0.0000

Data Index: 425687 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.1703. Min Act: -0.0000

Data Index: 254549 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 2.8378. Min Range: -2.8378

Max Act: 2.0353. Min Act: -0.0000

Data Index: 1176708 (C4 (Web Text))

Max Activating Token Index: 866