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

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

Neuron 214 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1602. Min Range: -1.1602

Max Act: 1.1602. Min Act: -0.0000

Data Index: 409611 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.9447. Min Act: -0.0000

Data Index: 59721 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.9863. Min Act: -0.0000

Data Index: 9172 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.9682. Min Act: -0.0000

Data Index: 747715 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.8710. Min Act: -0.0000

Data Index: 97960 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.9197. Min Act: -0.0000

Data Index: 469951 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.8468. Min Act: -0.0000

Data Index: 894051 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.8697. Min Act: -0.0000

Data Index: 626129 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.8516. Min Act: -0.0000

Data Index: 827116 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.8239. Min Act: -0.0000

Data Index: 1221542 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1135258 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.8368. Min Act: -0.0000

Data Index: 462568 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.7978. Min Act: -0.0000

Data Index: 211191 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1190142 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.8196. Min Act: -0.0000

Data Index: 672377 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.8097. Min Act: -0.0000

Data Index: 5150 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.7754. Min Act: -0.0000

Data Index: 323468 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.7983. Min Act: -0.0000

Data Index: 516840 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.7731. Min Act: -0.0000

Data Index: 557211 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 1.1602. Min Range: -1.1602

Max Act: 0.7455. Min Act: -0.0000

Data Index: 406405 (C4 (Web Text))

Max Activating Token Index: 338