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

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

Neuron 1683 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: 0.7110. Min Range: -0.7110

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1397324 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5853. Min Act: -0.0000

Data Index: 929430 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5441. Min Act: -0.0000

Data Index: 459916 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5227. Min Act: -0.0000

Data Index: 400597 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1075636 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5113. Min Act: -0.0000

Data Index: 958465 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1005203 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4713. Min Act: -0.0000

Data Index: 108412 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5018. Min Act: -0.0000

Data Index: 699176 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4938. Min Act: -0.0000

Data Index: 612734 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4619. Min Act: -0.0000

Data Index: 292343 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4442. Min Act: -0.0000

Data Index: 283424 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1625817 (Python Code)

Max Activating Token Index: 444

Text #13

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4347. Min Act: -0.0000

Data Index: 788222 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4282. Min Act: -0.0000

Data Index: 633838 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1621742 (Python Code)

Max Activating Token Index: 890

Text #16

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.3801. Min Act: -0.0000

Data Index: 782019 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.3400. Min Act: -0.0000

Data Index: 249542 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1428487 (Python Code)

Max Activating Token Index: 960

Text #19

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.3721. Min Act: -0.0000

Data Index: 913753 (C4 (Web Text))

Max Activating Token Index: 127