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

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

Neuron 5373 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: 0.6960. Min Range: -0.6960

Max Act: 0.6960. Min Act: -0.0000

Data Index: 556001 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1198522 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5516. Min Act: -0.0000

Data Index: 226781 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5851. Min Act: -0.0000

Data Index: 27405 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1354628 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5625. Min Act: -0.0000

Data Index: 42695 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5391. Min Act: -0.0000

Data Index: 674552 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5228. Min Act: -0.0000

Data Index: 901249 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1114831 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5539. Min Act: -0.0000

Data Index: 216272 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5119. Min Act: -0.0000

Data Index: 950154 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5142. Min Act: -0.0000

Data Index: 350273 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1359736 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5462. Min Act: -0.0000

Data Index: 710051 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5226. Min Act: -0.0000

Data Index: 53908 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5511. Min Act: -0.0000

Data Index: 782948 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1069858 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5515. Min Act: -0.0000

Data Index: 864539 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5479. Min Act: 0.0000

Data Index: 857807 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4995. Min Act: -0.0000

Data Index: 356520 (C4 (Web Text))

Max Activating Token Index: 577