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

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

Neuron 365 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1299033 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.6889. Min Act: -0.0000

Data Index: 150013 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1236227 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1186969 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5965. Min Act: -0.0000

Data Index: 751758 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5760. Min Act: -0.0000

Data Index: 936542 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5837. Min Act: -0.0000

Data Index: 246192 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5584. Min Act: -0.0000

Data Index: 860667 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5576. Min Act: -0.0000

Data Index: 889767 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.4777. Min Act: -0.0000

Data Index: 272734 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5219. Min Act: -0.0000

Data Index: 116878 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1165486 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.5102. Min Act: -0.0000

Data Index: 93775 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.4877. Min Act: -0.0000

Data Index: 433582 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.4481. Min Act: -0.0000

Data Index: 704333 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.4811. Min Act: -0.0000

Data Index: 144602 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.4562. Min Act: -0.0000

Data Index: 827164 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.4321. Min Act: -0.0000

Data Index: 883599 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.4111. Min Act: -0.0000

Data Index: 732419 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.7333. Min Range: -0.7333

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1246125 (C4 (Web Text))

Max Activating Token Index: 258