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

Dataset: The Pile

Neuron 2156 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.6175. Min Act: -0.0000

Data Index: 1199490 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.4254. Min Act: -0.0000

Data Index: 1093682 (The Pile)

Max Activating Token Index: 44

Text #2

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.4200. Min Act: -0.0000

Data Index: 1353128 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.7471. Min Act: -0.0000

Data Index: 1108650 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.3301. Min Act: -0.0000

Data Index: 913647 (The Pile)

Max Activating Token Index: 604

Text #5

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.2673. Min Act: -0.0000

Data Index: 275071 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.2103. Min Act: -0.0000

Data Index: 1246749 (The Pile)

Max Activating Token Index: 738

Text #7

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.3847. Min Act: -0.0000

Data Index: 1384602 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.0086. Min Act: -0.0000

Data Index: 719081 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.1610. Min Act: -0.0000

Data Index: 1666258 (The Pile)

Max Activating Token Index: 922

Text #10

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1007449 (The Pile)

Max Activating Token Index: 350

Text #11

Max Range: 1.7471. Min Range: -1.7471

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1502390 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.1138. Min Act: -0.0000

Data Index: 227439 (The Pile)

Max Activating Token Index: 912

Text #13

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.1433. Min Act: -0.0000

Data Index: 339736 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 1.7471. Min Range: -1.7471

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1163833 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.0826. Min Act: -0.0000

Data Index: 271565 (The Pile)

Max Activating Token Index: 179

Text #16

Max Range: 1.7471. Min Range: -1.7471

Max Act: 0.8743. Min Act: -0.0000

Data Index: 874405 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1690699 (The Pile)

Max Activating Token Index: 360

Text #18

Max Range: 1.7471. Min Range: -1.7471

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1135202 (The Pile)

Max Activating Token Index: 650

Text #19

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.0205. Min Act: -0.0000

Data Index: 15991 (The Pile)

Max Activating Token Index: 77