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

Dataset: The Pile

Neuron 1626 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.9843. Min Act: -0.0000

Data Index: 427861 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.9784. Min Act: -0.0000

Data Index: 1280354 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.7383. Min Act: -0.0000

Data Index: 627620 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.4173. Min Act: -0.0000

Data Index: 1332457 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.6489. Min Act: -0.0000

Data Index: 863005 (The Pile)

Max Activating Token Index: 949

Text #5

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.3895. Min Act: -0.0000

Data Index: 625171 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.3821. Min Act: -0.0000

Data Index: 902897 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.4304. Min Act: -0.0000

Data Index: 66150 (The Pile)

Max Activating Token Index: 434

Text #8

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.4189. Min Act: -0.0000

Data Index: 950389 (The Pile)

Max Activating Token Index: 134

Text #9

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.3628. Min Act: -0.0000

Data Index: 1878167 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1587937 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.2627. Min Act: -0.0000

Data Index: 1802861 (The Pile)

Max Activating Token Index: 708

Text #12

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.2533. Min Act: -0.0000

Data Index: 314146 (The Pile)

Max Activating Token Index: 520

Text #13

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.1975. Min Act: -0.0000

Data Index: 948279 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.3004. Min Act: -0.0000

Data Index: 1623544 (The Pile)

Max Activating Token Index: 641

Text #15

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.2188. Min Act: -0.0000

Data Index: 1950316 (The Pile)

Max Activating Token Index: 502

Text #16

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.2885. Min Act: -0.0000

Data Index: 1044411 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.1208. Min Act: -0.0000

Data Index: 1689449 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.1364. Min Act: -0.0000

Data Index: 833041 (The Pile)

Max Activating Token Index: 884

Text #19

Max Range: 1.9843. Min Range: -1.9843

Max Act: 1.2428. Min Act: -0.0000

Data Index: 1995067 (The Pile)

Max Activating Token Index: 590