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

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

Neuron 5320 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.9070. Min Act: -0.0000

Data Index: 123013 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1144592 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8917. Min Act: -0.0000

Data Index: 673273 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8781. Min Act: -0.0000

Data Index: 517552 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8052. Min Act: -0.0000

Data Index: 131501 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7586. Min Act: -0.0000

Data Index: 955492 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7185. Min Act: -0.0000

Data Index: 546852 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7119. Min Act: -0.0000

Data Index: 126910 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6500. Min Act: -0.0000

Data Index: 185097 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6465. Min Act: -0.0000

Data Index: 365446 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1019113 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1531740 (Python Code)

Max Activating Token Index: 1018

Text #12

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1021558 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1043665 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1356305 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5894. Min Act: -0.0000

Data Index: 178869 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5839. Min Act: -0.0000

Data Index: 492940 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5626. Min Act: -0.0000

Data Index: 22699 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1307540 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1382883 (Python Code)

Max Activating Token Index: 806