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

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

Neuron 155 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1185361 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.5759. Min Act: -0.0000

Data Index: 556405 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.2729. Min Act: -0.0000

Data Index: 500174 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.2640. Min Act: -0.0000

Data Index: 981777 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.2933. Min Act: -0.0000

Data Index: 262018 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.4045. Min Act: -0.0000

Data Index: 383133 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.2702. Min Act: -0.0000

Data Index: 1212704 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.1869. Min Act: -0.0000

Data Index: 917628 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.2691. Min Act: -0.0000

Data Index: 954373 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.2510. Min Act: -0.0000

Data Index: 1145087 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 1.7417. Min Range: -1.7417

Max Act: 0.9231. Min Act: -0.0000

Data Index: 680708 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.0395. Min Act: -0.0000

Data Index: 1232465 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 1.7417. Min Range: -1.7417

Max Act: 0.8906. Min Act: -0.0000

Data Index: 799878 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 1.7417. Min Range: -1.7417

Max Act: 0.8748. Min Act: -0.0000

Data Index: 865954 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1221736 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 1.7417. Min Range: -1.7417

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1233794 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 1.7417. Min Range: -1.7417

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1318695 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 1.7417. Min Range: -1.7417

Max Act: 0.9276. Min Act: -0.0000

Data Index: 725209 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 1.7417. Min Range: -1.7417

Max Act: 0.8989. Min Act: -0.0000

Data Index: 580559 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 1.7417. Min Range: -1.7417

Max Act: 0.7997. Min Act: -0.0000

Data Index: 791231 (C4 (Web Text))

Max Activating Token Index: 607