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

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

Neuron 2173 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.9729. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 2.1053. Min Range: -2.1053

Max Act: 2.0196. Min Act: -0.0000

Data Index: 510507 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.9926. Min Act: -0.0000

Data Index: 719456 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 2.1053. Min Range: -2.1053

Max Act: 2.1053. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.7692. Min Act: -0.0000

Data Index: 119026 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.7283. Min Act: -0.0000

Data Index: 521278 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 2.1053. Min Range: -2.1053

Max Act: 2.0397. Min Act: -0.0000

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.6667. Min Act: -0.0000

Data Index: 1108840 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.4912. Min Act: -0.0000

Data Index: 412891 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.4099. Min Act: -0.0000

Data Index: 271985 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.4608. Min Act: -0.0000

Data Index: 947929 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.5420. Min Act: -0.0000

Data Index: 929076 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.4002. Min Act: -0.0000

Data Index: 782999 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.3909. Min Act: -0.0000

Data Index: 659792 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.3759. Min Act: -0.0000

Data Index: 91387 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.2908. Min Act: -0.0000

Data Index: 1640423 (Python Code)

Max Activating Token Index: 841

Text #16

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.3590. Min Act: -0.0000

Data Index: 978198 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.3045. Min Act: -0.0000

Data Index: 265839 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.2068. Min Act: -0.0000

Data Index: 701059 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 2.1053. Min Range: -2.1053

Max Act: 1.1588. Min Act: -0.0000

Data Index: 890171 (C4 (Web Text))

Max Activating Token Index: 1023