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

Dataset: The Pile

Neuron 760 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: 0.4415. Min Range: -0.4415

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1451811 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1887304 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3717. Min Act: -0.0000

Data Index: 879078 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.4415. Min Act: -0.0000

Data Index: 199817 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1627619 (The Pile)

Max Activating Token Index: 505

Text #5

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3821. Min Act: -0.0000

Data Index: 677399 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3896. Min Act: -0.0000

Data Index: 98355 (The Pile)

Max Activating Token Index: 767

Text #7

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3594. Min Act: -0.0000

Data Index: 755679 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3724. Min Act: -0.0000

Data Index: 515137 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3516. Min Act: -0.0000

Data Index: 199845 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3620. Min Act: -0.0000

Data Index: 82949 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3299. Min Act: -0.0000

Data Index: 772684 (The Pile)

Max Activating Token Index: 891

Text #12

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1337944 (The Pile)

Max Activating Token Index: 281

Text #13

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3917. Min Act: -0.0000

Data Index: 1041859 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1733717 (The Pile)

Max Activating Token Index: 818

Text #15

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1191378 (The Pile)

Max Activating Token Index: 964

Text #16

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1845545 (The Pile)

Max Activating Token Index: 91

Text #17

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3488. Min Act: -0.0000

Data Index: 643310 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2986. Min Act: -0.0000

Data Index: 463054 (The Pile)

Max Activating Token Index: 203

Text #19

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1351026 (The Pile)

Max Activating Token Index: 208