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

Dataset: The Pile

Neuron 4027 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3297. Min Range: -1.3297

Max Act: 1.3297. Min Act: -0.0000

Data Index: 1472148 (The Pile)

Max Activating Token Index: 174

Text #1

Max Range: 1.3297. Min Range: -1.3297

Max Act: 1.0374. Min Act: -0.0000

Data Index: 1302302 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8983. Min Act: -0.0000

Data Index: 951094 (The Pile)

Max Activating Token Index: 358

Text #3

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.9195. Min Act: -0.0000

Data Index: 85403 (The Pile)

Max Activating Token Index: 73

Text #4

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1728785 (The Pile)

Max Activating Token Index: 874

Text #5

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.9042. Min Act: -0.0000

Data Index: 685394 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1968723 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7824. Min Act: -0.0000

Data Index: 484686 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1028257 (The Pile)

Max Activating Token Index: 65

Text #9

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8397. Min Act: -0.0000

Data Index: 721093 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8143. Min Act: -0.0000

Data Index: 629266 (The Pile)

Max Activating Token Index: 380

Text #11

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7909. Min Act: -0.0000

Data Index: 89180 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7631. Min Act: -0.0000

Data Index: 750569 (The Pile)

Max Activating Token Index: 244

Text #13

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1054825 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1413267 (The Pile)

Max Activating Token Index: 247

Text #15

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1475344 (The Pile)

Max Activating Token Index: 886

Text #16

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7866. Min Act: -0.0000

Data Index: 106575 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7277. Min Act: -0.0000

Data Index: 453880 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.6949. Min Act: -0.0000

Data Index: 328008 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1442261 (The Pile)

Max Activating Token Index: 594