Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2406 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.1672. Min Act: -0.0001

Data Index: 715389 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.1199. Min Act: -0.0001

Data Index: 990600 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.0764. Min Act: -0.0001

Data Index: 1160746 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.1502. Min Act: -0.0001

Data Index: 458189 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.0490. Min Act: -0.0001

Data Index: 1292859 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9413. Min Act: -0.0001

Data Index: 575268 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9456. Min Act: -0.0001

Data Index: 708941 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9970. Min Act: -0.0001

Data Index: 1352888 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9369. Min Act: -0.0001

Data Index: 471484 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9891. Min Act: -0.0001

Data Index: 959124 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9918. Min Act: -0.0001

Data Index: 331430 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9456. Min Act: -0.0001

Data Index: 746985 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9687. Min Act: -0.0001

Data Index: 1066200 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9413. Min Act: -0.0001

Data Index: 1025910 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8891. Min Act: -0.0001

Data Index: 1074785 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8060. Min Act: -0.0001

Data Index: 247662 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9112. Min Act: -0.0001

Data Index: 758097 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9314. Min Act: -0.0001

Data Index: 208423 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9054. Min Act: -0.0001

Data Index: 622194 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8809. Min Act: -0.0001

Data Index: 607737 (C4 (Web Text))

Max Activating Token Index: 651