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

Dataset: The Pile

Neuron 601 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4904. Min Act: -0.0000

Data Index: 365169 (The Pile)

Max Activating Token Index: 367

Text #1

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4637. Min Act: -0.0000

Data Index: 565764 (The Pile)

Max Activating Token Index: 527

Text #2

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4173. Min Act: -0.0000

Data Index: 449502 (The Pile)

Max Activating Token Index: 346

Text #3

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3974. Min Act: -0.0000

Data Index: 669054 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1334388 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1571828 (The Pile)

Max Activating Token Index: 418

Text #6

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1075860 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4052. Min Act: -0.0000

Data Index: 208528 (The Pile)

Max Activating Token Index: 197

Text #8

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1719509 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4146. Min Act: -0.0000

Data Index: 651321 (The Pile)

Max Activating Token Index: 707

Text #10

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4163. Min Act: -0.0000

Data Index: 937960 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1357797 (The Pile)

Max Activating Token Index: 506

Text #12

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3786. Min Act: -0.0000

Data Index: 467740 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3652. Min Act: -0.0000

Data Index: 343301 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1354702 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1926787 (The Pile)

Max Activating Token Index: 909

Text #16

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1845450 (The Pile)

Max Activating Token Index: 124

Text #17

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1784574 (The Pile)

Max Activating Token Index: 351

Text #18

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1639513 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3558. Min Act: -0.0000

Data Index: 331103 (The Pile)

Max Activating Token Index: 793