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

Dataset: The Pile

Neuron 3236 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.7126. Min Act: -0.0000

Data Index: 1434344 (The Pile)

Max Activating Token Index: 775

Text #1

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.8591. Min Act: -0.0000

Data Index: 419452 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6248. Min Act: -0.0000

Data Index: 1870983 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.4045. Min Act: -0.0000

Data Index: 1644269 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.5407. Min Act: -0.0000

Data Index: 1522804 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6563. Min Act: -0.0000

Data Index: 1951201 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.4539. Min Act: -0.0000

Data Index: 1592577 (The Pile)

Max Activating Token Index: 379

Text #7

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.4002. Min Act: -0.0000

Data Index: 1344424 (The Pile)

Max Activating Token Index: 168

Text #8

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.3880. Min Act: -0.0000

Data Index: 214778 (The Pile)

Max Activating Token Index: 343

Text #9

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.2111. Min Act: -0.0000

Data Index: 1393405 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.2102. Min Act: -0.0000

Data Index: 593962 (The Pile)

Max Activating Token Index: 683

Text #11

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.3326. Min Act: -0.0000

Data Index: 941182 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.0028. Min Act: -0.0000

Data Index: 658081 (The Pile)

Max Activating Token Index: 318

Text #13

Max Range: 3.8591. Min Range: -3.8591

Max Act: 2.9248. Min Act: -0.0000

Data Index: 316661 (The Pile)

Max Activating Token Index: 587

Text #14

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.0275. Min Act: -0.0000

Data Index: 660902 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.1709. Min Act: -0.0000

Data Index: 1228676 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.1131. Min Act: -0.0000

Data Index: 1607157 (The Pile)

Max Activating Token Index: 752

Text #17

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.1449. Min Act: -0.0000

Data Index: 537391 (The Pile)

Max Activating Token Index: 948

Text #18

Max Range: 3.8591. Min Range: -3.8591

Max Act: 2.9163. Min Act: -0.0000

Data Index: 1059380 (The Pile)

Max Activating Token Index: 883

Text #19

Max Range: 3.8591. Min Range: -3.8591

Max Act: 2.9501. Min Act: -0.0000

Data Index: 1457528 (The Pile)

Max Activating Token Index: 543