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

Dataset: The Pile

Neuron 3830 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1480230 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6399. Min Act: -0.0000

Data Index: 742852 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5248. Min Act: -0.0000

Data Index: 881028 (The Pile)

Max Activating Token Index: 611

Text #3

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1884985 (The Pile)

Max Activating Token Index: 577

Text #4

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5600. Min Act: -0.0000

Data Index: 203373 (The Pile)

Max Activating Token Index: 502

Text #5

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5611. Min Act: 0.0000

Data Index: 332510 (The Pile)

Max Activating Token Index: 741

Text #6

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5564. Min Act: -0.0000

Data Index: 348265 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5694. Min Act: -0.0000

Data Index: 509085 (The Pile)

Max Activating Token Index: 913

Text #8

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4938. Min Act: -0.0000

Data Index: 57462 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5593. Min Act: -0.0000

Data Index: 499089 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1257650 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1748850 (The Pile)

Max Activating Token Index: 979

Text #12

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1595182 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1295567 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1536361 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1293310 (The Pile)

Max Activating Token Index: 715

Text #16

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4045. Min Act: 0.0000

Data Index: 160749 (The Pile)

Max Activating Token Index: 909

Text #17

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.3376. Min Act: -0.0000

Data Index: 49970 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.3495. Min Act: -0.0000

Data Index: 977009 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1147789 (The Pile)

Max Activating Token Index: 398