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

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

Neuron 3677 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.5454. Min Act: -0.0000

Data Index: 598391 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.5059. Min Act: -0.0000

Data Index: 502324 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1235571 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.5053. Min Act: -0.0000

Data Index: 753606 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1014842 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1012083 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4807. Min Act: -0.0000

Data Index: 322709 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.5089. Min Act: -0.0000

Data Index: 196837 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4486. Min Act: -0.0000

Data Index: 527718 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4522. Min Act: -0.0000

Data Index: 331004 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4897. Min Act: -0.0000

Data Index: 869686 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4373. Min Act: -0.0000

Data Index: 383484 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1327639 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4470. Min Act: -0.0000

Data Index: 802206 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4157. Min Act: -0.0000

Data Index: 992910 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4434. Min Act: -0.0000

Data Index: 848770 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1091187 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1240538 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4234. Min Act: -0.0000

Data Index: 43266 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.3981. Min Act: -0.0000

Data Index: 532448 (C4 (Web Text))

Max Activating Token Index: 853