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

Dataset: The Pile

Neuron 2230 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: 3.2297. Min Range: -3.2297

Max Act: 3.2297. Min Act: -0.0000

Data Index: 259826 (The Pile)

Max Activating Token Index: 240

Text #1

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.3672. Min Act: -0.0000

Data Index: 341823 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.3405. Min Act: -0.0000

Data Index: 1611370 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.4702. Min Act: -0.0000

Data Index: 1621395 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.2813. Min Act: -0.0000

Data Index: 1229671 (The Pile)

Max Activating Token Index: 890

Text #5

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.0170. Min Act: -0.0000

Data Index: 1580032 (The Pile)

Max Activating Token Index: 772

Text #6

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.1105. Min Act: -0.0000

Data Index: 1499819 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.2017. Min Act: -0.0000

Data Index: 344809 (The Pile)

Max Activating Token Index: 423

Text #8

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.1666. Min Act: -0.0000

Data Index: 1816505 (The Pile)

Max Activating Token Index: 895

Text #9

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.0043. Min Act: -0.0000

Data Index: 1140246 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 3.2297. Min Range: -3.2297

Max Act: 1.9239. Min Act: -0.0000

Data Index: 1081519 (The Pile)

Max Activating Token Index: 138

Text #11

Max Range: 3.2297. Min Range: -3.2297

Max Act: 1.9364. Min Act: -0.0000

Data Index: 462822 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.1389. Min Act: -0.0000

Data Index: 1279982 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.1370. Min Act: -0.0000

Data Index: 1575869 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 3.2297. Min Range: -3.2297

Max Act: 1.9000. Min Act: -0.0000

Data Index: 166634 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.0201. Min Act: -0.0000

Data Index: 393654 (The Pile)

Max Activating Token Index: 75

Text #16

Max Range: 3.2297. Min Range: -3.2297

Max Act: 1.9558. Min Act: -0.0000

Data Index: 1444693 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 3.2297. Min Range: -3.2297

Max Act: 1.9414. Min Act: -0.0000

Data Index: 214029 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 3.2297. Min Range: -3.2297

Max Act: 2.0003. Min Act: -0.0000

Data Index: 1886536 (The Pile)

Max Activating Token Index: 273

Text #19

Max Range: 3.2297. Min Range: -3.2297

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1922025 (The Pile)

Max Activating Token Index: 636