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

Dataset: The Pile

Neuron 1413 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.6294. Min Act: -0.0000

Data Index: 1152583 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.6819. Min Act: -0.0000

Data Index: 1557756 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.5626. Min Act: -0.0000

Data Index: 1407811 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.4876. Min Act: -0.0000

Data Index: 184527 (The Pile)

Max Activating Token Index: 87

Text #4

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.4414. Min Act: -0.0000

Data Index: 1800881 (The Pile)

Max Activating Token Index: 307

Text #5

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.7211. Min Act: -0.0000

Data Index: 951356 (The Pile)

Max Activating Token Index: 627

Text #6

Max Range: 3.7211. Min Range: -3.7211

Max Act: 2.9768. Min Act: -0.0000

Data Index: 1664009 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.0046. Min Act: -0.0000

Data Index: 139243 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.0528. Min Act: -0.0000

Data Index: 52484 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.1833. Min Act: -0.0000

Data Index: 1745377 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 3.7211. Min Range: -3.7211

Max Act: 2.8273. Min Act: -0.0000

Data Index: 1576761 (The Pile)

Max Activating Token Index: 548

Text #11

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.1559. Min Act: -0.0000

Data Index: 1917279 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.0860. Min Act: -0.0000

Data Index: 1075860 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.1994. Min Act: -0.0000

Data Index: 926765 (The Pile)

Max Activating Token Index: 477

Text #14

Max Range: 3.7211. Min Range: -3.7211

Max Act: 3.0088. Min Act: -0.0000

Data Index: 1423865 (The Pile)

Max Activating Token Index: 802

Text #15

Max Range: 3.7211. Min Range: -3.7211

Max Act: 2.8491. Min Act: -0.0000

Data Index: 394179 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 3.7211. Min Range: -3.7211

Max Act: 2.7782. Min Act: -0.0000

Data Index: 1357282 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 3.7211. Min Range: -3.7211

Max Act: 2.9143. Min Act: -0.0000

Data Index: 1675604 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 3.7211. Min Range: -3.7211

Max Act: 2.6429. Min Act: -0.0000

Data Index: 1936235 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 3.7211. Min Range: -3.7211

Max Act: 2.5166. Min Act: -0.0000

Data Index: 1991071 (The Pile)

Max Activating Token Index: 368