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

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

Neuron 4808 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1158433 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2276. Min Act: -0.0000

Data Index: 1194627 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2022. Min Act: -0.0000

Data Index: 150565 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1834. Min Act: -0.0000

Data Index: 574202 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1244894 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1254117 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1865. Min Act: -0.0000

Data Index: 188326 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1993. Min Act: -0.0000

Data Index: 177014 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1979. Min Act: -0.0000

Data Index: 939658 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1281861 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1320063 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1855. Min Act: -0.0000

Data Index: 144761 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1831. Min Act: -0.0000

Data Index: 570610 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1937. Min Act: -0.0000

Data Index: 727676 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2015. Min Act: -0.0000

Data Index: 880603 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1856. Min Act: -0.0000

Data Index: 559111 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1781. Min Act: -0.0000

Data Index: 420041 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1806. Min Act: -0.0000

Data Index: 243797 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1802. Min Act: -0.0000

Data Index: 689218 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1752. Min Act: -0.0000

Data Index: 177567 (C4 (Web Text))

Max Activating Token Index: 649