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

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

Neuron 6097 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.8457. Min Act: -0.0000

Data Index: 1134862 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.7273. Min Act: -0.0000

Data Index: 536218 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.6802. Min Act: -0.0000

Data Index: 1288993 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.6595. Min Act: -0.0000

Data Index: 312454 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 3.0309. Min Range: -3.0309

Max Act: 3.0309. Min Act: -0.0000

Data Index: 1157067 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.3797. Min Act: -0.0000

Data Index: 872003 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.0806. Min Act: -0.0000

Data Index: 551528 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.1663. Min Act: -0.0000

Data Index: 1255341 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.3484. Min Act: -0.0000

Data Index: 904900 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.3348. Min Act: -0.0000

Data Index: 9309 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.3705. Min Act: -0.0000

Data Index: 651822 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.0932. Min Act: -0.0000

Data Index: 1108683 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 3.0309. Min Range: -3.0309

Max Act: 1.8900. Min Act: -0.0000

Data Index: 750913 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.0589. Min Act: -0.0000

Data Index: 1015080 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.2602. Min Act: -0.0000

Data Index: 1296280 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.1639. Min Act: -0.0000

Data Index: 827937 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.1606. Min Act: -0.0000

Data Index: 845160 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.0986. Min Act: -0.0000

Data Index: 1167966 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 3.0309. Min Range: -3.0309

Max Act: 2.0913. Min Act: -0.0000

Data Index: 158841 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 3.0309. Min Range: -3.0309

Max Act: 1.9055. Min Act: -0.0000

Data Index: 1315867 (C4 (Web Text))

Max Activating Token Index: 973