Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1280 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9538. Min Act: -0.0001

Data Index: 1076571 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.8792. Min Act: -0.0001

Data Index: 566188 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.8714. Min Act: -0.0001

Data Index: 50987 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.8198. Min Act: -0.0001

Data Index: 847925 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.8358. Min Act: -0.0001

Data Index: 481982 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.8039. Min Act: -0.0001

Data Index: 47799 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.7950. Min Act: -0.0001

Data Index: 1154176 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.6579. Min Act: -0.0001

Data Index: 101588 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.6361. Min Act: -0.0001

Data Index: 350642 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.6199. Min Act: -0.0001

Data Index: 193671 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.6241. Min Act: -0.0001

Data Index: 420645 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.6118. Min Act: -0.0001

Data Index: 1024217 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.5880. Min Act: -0.0001

Data Index: 659925 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.5632. Min Act: -0.0001

Data Index: 1150875 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.5403. Min Act: -0.0001

Data Index: 1116695 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.5069. Min Act: -0.0001

Data Index: 300340 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.4948. Min Act: -0.0001

Data Index: 595507 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.4887. Min Act: -0.0001

Data Index: 1315877 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.5001. Min Act: -0.0001

Data Index: 1313108 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.5357. Min Act: -0.0001

Data Index: 184103 (C4 (Web Text))

Max Activating Token Index: 650