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

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

Neuron 3270 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2450. Min Range: -2.2450

Max Act: 2.2446. Min Act: -0.0000

Data Index: 39775 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 2.2450. Min Range: -2.2450

Max Act: 2.2450. Min Act: -0.0000

Data Index: 1101018 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 2.2450. Min Range: -2.2450

Max Act: 2.1069. Min Act: -0.0001

Data Index: 1044877 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 2.2450. Min Range: -2.2450

Max Act: 2.0632. Min Act: -0.0000

Data Index: 482160 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 2.2450. Min Range: -2.2450

Max Act: 2.0512. Min Act: -0.0001

Data Index: 481950 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 2.2450. Min Range: -2.2450

Max Act: 2.0175. Min Act: -0.0001

Data Index: 318755 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.8019. Min Act: -0.0001

Data Index: 1298360 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.6569. Min Act: -0.0001

Data Index: 1303850 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.7436. Min Act: -0.0001

Data Index: 524311 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.7404. Min Act: -0.0001

Data Index: 774101 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.6344. Min Act: -0.0001

Data Index: 470961 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.8044. Min Act: -0.0001

Data Index: 620912 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.6885. Min Act: -0.0001

Data Index: 107369 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.8691. Min Act: -0.0001

Data Index: 798013 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.6842. Min Act: -0.0000

Data Index: 303850 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.6827. Min Act: -0.0001

Data Index: 1295508 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.5874. Min Act: -0.0001

Data Index: 38247 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.4741. Min Act: -0.0001

Data Index: 1204808 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.6234. Min Act: -0.0001

Data Index: 346471 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 2.2450. Min Range: -2.2450

Max Act: 1.7019. Min Act: -0.0000

Data Index: 1341924 (C4 (Web Text))

Max Activating Token Index: 355