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

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

Neuron 554 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: 2.2948. Min Range: -2.2948

Max Act: 2.1592. Min Act: -0.0000

Data Index: 976116 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.9757. Min Act: -0.0000

Data Index: 1335693 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.9706. Min Act: -0.0000

Data Index: 800426 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.6839. Min Act: -0.0000

Data Index: 1195210 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 2.2948. Min Range: -2.2948

Max Act: 2.2948. Min Act: -0.0000

Data Index: 1047199 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.9057. Min Act: -0.0000

Data Index: 945206 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.6985. Min Act: -0.0000

Data Index: 1040622 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.7969. Min Act: -0.0000

Data Index: 772135 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.6683. Min Act: -0.0000

Data Index: 628004 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.7971. Min Act: -0.0000

Data Index: 943013 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.6222. Min Act: -0.0000

Data Index: 844496 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.6660. Min Act: -0.0000

Data Index: 1342819 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.8920. Min Act: -0.0000

Data Index: 357449 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.6158. Min Act: -0.0000

Data Index: 159611 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.6124. Min Act: -0.0000

Data Index: 292664 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.5182. Min Act: -0.0000

Data Index: 254476 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.6024. Min Act: -0.0000

Data Index: 913192 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.6290. Min Act: -0.0000

Data Index: 38042 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.3737. Min Act: -0.0000

Data Index: 1334619 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 2.2948. Min Range: -2.2948

Max Act: 1.5878. Min Act: -0.0000

Data Index: 851207 (C4 (Web Text))

Max Activating Token Index: 306