Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4913 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4639. Min Range: -1.4639

Max Act: 1.4639. Min Act: -0.0000

Data Index: 914241 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.4639. Min Range: -1.4639

Max Act: 1.1862. Min Act: -0.0000

Data Index: 123130 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 1.4639. Min Range: -1.4639

Max Act: 1.2310. Min Act: -0.0000

Data Index: 345385 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 1.4639. Min Range: -1.4639

Max Act: 1.1942. Min Act: -0.0000

Data Index: 169676 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.4639. Min Range: -1.4639

Max Act: 1.1348. Min Act: -0.0000

Data Index: 1056729 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 1.4639. Min Range: -1.4639

Max Act: 1.0821. Min Act: -0.0000

Data Index: 152978 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 1.4639. Min Range: -1.4639

Max Act: 1.0451. Min Act: -0.0000

Data Index: 73972 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 1.4639. Min Range: -1.4639

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1295127 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.4639. Min Range: -1.4639

Max Act: 0.9609. Min Act: -0.0000

Data Index: 88098 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 1.4639. Min Range: -1.4639

Max Act: 0.9895. Min Act: -0.0000

Data Index: 1025014 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 1.4639. Min Range: -1.4639

Max Act: 1.0073. Min Act: -0.0000

Data Index: 357817 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 1.4639. Min Range: -1.4639

Max Act: 1.0825. Min Act: -0.0000

Data Index: 159420 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 1.4639. Min Range: -1.4639

Max Act: 0.9540. Min Act: -0.0000

Data Index: 625417 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 1.4639. Min Range: -1.4639

Max Act: 0.9686. Min Act: -0.0000

Data Index: 222825 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.4639. Min Range: -1.4639

Max Act: 0.9136. Min Act: -0.0000

Data Index: 888795 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 1.4639. Min Range: -1.4639

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1045199 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 1.4639. Min Range: -1.4639

Max Act: 1.0068. Min Act: -0.0000

Data Index: 263918 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.4639. Min Range: -1.4639

Max Act: 0.9368. Min Act: -0.0000

Data Index: 431223 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 1.4639. Min Range: -1.4639

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1071940 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 1.4639. Min Range: -1.4639

Max Act: 0.9329. Min Act: -0.0000

Data Index: 621379 (C4 (Web Text))

Max Activating Token Index: 328