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

Dataset: The Pile

Neuron 1253 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.5300. Min Act: -0.0000

Data Index: 511462 (The Pile)

Max Activating Token Index: 306

Text #1

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.0716. Min Act: -0.0000

Data Index: 1713071 (The Pile)

Max Activating Token Index: 157

Text #2

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.9010. Min Act: -0.0000

Data Index: 1284235 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.8706. Min Act: -0.0000

Data Index: 312849 (The Pile)

Max Activating Token Index: 75

Text #4

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.8380. Min Act: -0.0000

Data Index: 1386369 (The Pile)

Max Activating Token Index: 751

Text #5

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.6472. Min Act: -0.0000

Data Index: 606064 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.4802. Min Act: -0.0000

Data Index: 12158 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.7075. Min Act: -0.0000

Data Index: 275050 (The Pile)

Max Activating Token Index: 230

Text #8

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.8243. Min Act: -0.0000

Data Index: 1708082 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.5456. Min Act: -0.0000

Data Index: 1194809 (The Pile)

Max Activating Token Index: 48

Text #10

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.6648. Min Act: -0.0000

Data Index: 1892853 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.6873. Min Act: -0.0000

Data Index: 600165 (The Pile)

Max Activating Token Index: 255

Text #12

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.6578. Min Act: -0.0000

Data Index: 1200430 (The Pile)

Max Activating Token Index: 34

Text #13

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.6558. Min Act: -0.0000

Data Index: 617158 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.6218. Min Act: -0.0000

Data Index: 227232 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.6351. Min Act: -0.0000

Data Index: 1109385 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.5962. Min Act: -0.0000

Data Index: 527797 (The Pile)

Max Activating Token Index: 977

Text #17

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.6088. Min Act: -0.0000

Data Index: 1172439 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.4742. Min Act: -0.0000

Data Index: 1052141 (The Pile)

Max Activating Token Index: 31

Text #19

Max Range: 3.5300. Min Range: -3.5300

Max Act: 2.5970. Min Act: -0.0000

Data Index: 1180954 (The Pile)

Max Activating Token Index: 395