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

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

Neuron 840 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: 5.0609. Min Range: -5.0609

Max Act: 5.0609. Min Act: -0.0000

Data Index: 1018743 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 5.0609. Min Range: -5.0609

Max Act: 4.5012. Min Act: -0.0000

Data Index: 190888 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 5.0609. Min Range: -5.0609

Max Act: 4.3264. Min Act: -0.0000

Data Index: 456555 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 5.0609. Min Range: -5.0609

Max Act: 4.2058. Min Act: -0.0000

Data Index: 585901 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 5.0609. Min Range: -5.0609

Max Act: 3.7731. Min Act: -0.0000

Data Index: 414674 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 5.0609. Min Range: -5.0609

Max Act: 3.7458. Min Act: -0.0000

Data Index: 236463 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 5.0609. Min Range: -5.0609

Max Act: 3.6903. Min Act: -0.0000

Data Index: 754430 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 5.0609. Min Range: -5.0609

Max Act: 3.3280. Min Act: -0.0000

Data Index: 881602 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 5.0609. Min Range: -5.0609

Max Act: 3.5966. Min Act: -0.0000

Data Index: 671431 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 5.0609. Min Range: -5.0609

Max Act: 3.4034. Min Act: -0.0000

Data Index: 392146 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 5.0609. Min Range: -5.0609

Max Act: 3.3032. Min Act: -0.0000

Data Index: 649855 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 5.0609. Min Range: -5.0609

Max Act: 3.4219. Min Act: -0.0000

Data Index: 1127169 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 5.0609. Min Range: -5.0609

Max Act: 3.3215. Min Act: -0.0000

Data Index: 292778 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 5.0609. Min Range: -5.0609

Max Act: 3.0694. Min Act: -0.0000

Data Index: 638807 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 5.0609. Min Range: -5.0609

Max Act: 3.0160. Min Act: -0.0000

Data Index: 335588 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 5.0609. Min Range: -5.0609

Max Act: 2.9650. Min Act: -0.0000

Data Index: 606481 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 5.0609. Min Range: -5.0609

Max Act: 3.0288. Min Act: -0.0000

Data Index: 753122 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 5.0609. Min Range: -5.0609

Max Act: 2.8846. Min Act: -0.0000

Data Index: 1307025 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 5.0609. Min Range: -5.0609

Max Act: 2.9891. Min Act: -0.0000

Data Index: 806831 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 5.0609. Min Range: -5.0609

Max Act: 2.8400. Min Act: -0.0000

Data Index: 1016304 (C4 (Web Text))

Max Activating Token Index: 572