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

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

Neuron 389 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1065. Min Act: -0.0001

Data Index: 720646 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1277264 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0856. Min Act: -0.0001

Data Index: 59325 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1061. Min Act: -0.0002

Data Index: 425455 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0858. Min Act: -0.0002

Data Index: 376678 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0945. Min Act: -0.0002

Data Index: 516885 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1030320 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1144836 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1279320 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1233514 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0874. Min Act: -0.0001

Data Index: 270556 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1149583 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0924. Min Act: -0.0002

Data Index: 414724 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0900. Min Act: -0.0001

Data Index: 150358 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0861. Min Act: -0.0001

Data Index: 698487 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0861. Min Act: -0.0002

Data Index: 896538 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1277426 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0781. Min Act: -0.0002

Data Index: 316351 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0737. Min Act: -0.0002

Data Index: 476152 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0670. Min Act: -0.0002

Data Index: 505656 (C4 (Web Text))

Max Activating Token Index: 957