Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5102 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.8327. Min Act: -0.0000

Data Index: 502656 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.7934. Min Act: -0.0000

Data Index: 1151485 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.8604. Min Act: -0.0000

Data Index: 397844 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 2.1642. Min Range: -2.1642

Max Act: 2.1642. Min Act: -0.0000

Data Index: 1069781 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.8759. Min Act: -0.0000

Data Index: 245834 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.7906. Min Act: -0.0000

Data Index: 1026706 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.8795. Min Act: -0.0000

Data Index: 1194728 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.9495. Min Act: -0.0000

Data Index: 1178342 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.8922. Min Act: -0.0000

Data Index: 1212014 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.8045. Min Act: -0.0000

Data Index: 1154952 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.8134. Min Act: -0.0000

Data Index: 1080021 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.8606. Min Act: -0.0000

Data Index: 586231 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.6733. Min Act: -0.0000

Data Index: 1149845 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.6641. Min Act: -0.0000

Data Index: 1525947 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.8522. Min Act: -0.0000

Data Index: 729328 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.7194. Min Act: -0.0000

Data Index: 650520 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.6239. Min Act: -0.0000

Data Index: 562830 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.8039. Min Act: -0.0000

Data Index: 484173 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.6351. Min Act: -0.0000

Data Index: 1054323 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.5687. Min Act: -0.0000

Data Index: 1177867 (C4 (Web Text))

Max Activating Token Index: 697