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

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

Neuron 3474 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2800. Min Range: -1.2800

Max Act: 1.2800. Min Act: -0.0000

Data Index: 40864 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 1.2800. Min Range: -1.2800

Max Act: 1.1627. Min Act: -0.0000

Data Index: 1070772 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 1.2800. Min Range: -1.2800

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1222098 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 1.2800. Min Range: -1.2800

Max Act: 1.0642. Min Act: -0.0000

Data Index: 995762 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 1.2800. Min Range: -1.2800

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1145271 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 1.2800. Min Range: -1.2800

Max Act: 1.0912. Min Act: -0.0000

Data Index: 1541307 (Python Code)

Max Activating Token Index: 853

Text #6

Max Range: 1.2800. Min Range: -1.2800

Max Act: 1.0253. Min Act: -0.0000

Data Index: 27843 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 1.2800. Min Range: -1.2800

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1233179 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 1.2800. Min Range: -1.2800

Max Act: 0.9537. Min Act: -0.0000

Data Index: 198437 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 1.2800. Min Range: -1.2800

Max Act: 1.0476. Min Act: -0.0000

Data Index: 81265 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 1.2800. Min Range: -1.2800

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1165142 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 1.2800. Min Range: -1.2800

Max Act: 1.0090. Min Act: -0.0000

Data Index: 470784 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 1.2800. Min Range: -1.2800

Max Act: 0.9729. Min Act: -0.0000

Data Index: 405786 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.2800. Min Range: -1.2800

Max Act: 1.0145. Min Act: -0.0000

Data Index: 355610 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 1.2800. Min Range: -1.2800

Max Act: 0.9300. Min Act: -0.0000

Data Index: 559623 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 1.2800. Min Range: -1.2800

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1198646 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 1.2800. Min Range: -1.2800

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1094002 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 1.2800. Min Range: -1.2800

Max Act: 0.8684. Min Act: -0.0000

Data Index: 613269 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 1.2800. Min Range: -1.2800

Max Act: 0.8953. Min Act: -0.0000

Data Index: 429182 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.2800. Min Range: -1.2800

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1067034 (C4 (Web Text))

Max Activating Token Index: 800