Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 700 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1444. Min Range: -1.1444

Max Act: 1.1444. Min Act: -0.0001

Data Index: 667975 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 1.1444. Min Range: -1.1444

Max Act: 1.0558. Min Act: -0.0000

Data Index: 831303 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9978. Min Act: -0.0000

Data Index: 732231 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 1.1444. Min Range: -1.1444

Max Act: 1.0173. Min Act: -0.0001

Data Index: 774074 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 1.1444. Min Range: -1.1444

Max Act: 1.0103. Min Act: -0.0000

Data Index: 749171 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 1.1444. Min Range: -1.1444

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1146941 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 1.1444. Min Range: -1.1444

Max Act: 1.0353. Min Act: -0.0000

Data Index: 1093671 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 1.1444. Min Range: -1.1444

Max Act: 1.0221. Min Act: -0.0000

Data Index: 175799 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9821. Min Act: -0.0000

Data Index: 716587 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 1.1444. Min Range: -1.1444

Max Act: 1.0136. Min Act: -0.0000

Data Index: 540700 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9768. Min Act: -0.0000

Data Index: 898431 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9599. Min Act: -0.0001

Data Index: 728052 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1224965 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1356904 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9218. Min Act: -0.0000

Data Index: 819246 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9215. Min Act: -0.0001

Data Index: 459279 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1019745 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9433. Min Act: -0.0001

Data Index: 227140 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1286389 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 1.1444. Min Range: -1.1444

Max Act: 0.9426. Min Act: -0.0001

Data Index: 513898 (C4 (Web Text))

Max Activating Token Index: 449