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

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

Neuron 2266 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1381236 (Python Code)

Max Activating Token Index: 515

Text #1

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1273344 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2648. Min Act: -0.0000

Data Index: 661028 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2205. Min Act: -0.0000

Data Index: 187133 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2303. Min Act: -0.0000

Data Index: 962820 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2327. Min Act: -0.0000

Data Index: 357595 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1139506 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2400. Min Act: -0.0000

Data Index: 455147 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2231. Min Act: -0.0000

Data Index: 726646 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1323714 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2093. Min Act: -0.0000

Data Index: 447808 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2191. Min Act: -0.0000

Data Index: 258318 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2168. Min Act: -0.0000

Data Index: 795532 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1825. Min Act: -0.0000

Data Index: 734560 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2099. Min Act: -0.0000

Data Index: 773777 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1486639 (Python Code)

Max Activating Token Index: 739

Text #16

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1929. Min Act: -0.0000

Data Index: 734678 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1753. Min Act: -0.0000

Data Index: 807593 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1510377 (Python Code)

Max Activating Token Index: 911

Text #19

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1351781 (C4 (Web Text))

Max Activating Token Index: 684