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

Dataset: The Pile

Neuron 4372 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: 1.7427. Min Range: -1.7427

Max Act: 1.7427. Min Act: -0.0000

Data Index: 1437973 (The Pile)

Max Activating Token Index: 344

Text #1

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.3336. Min Act: -0.0000

Data Index: 1339347 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1005527 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.1540. Min Act: -0.0000

Data Index: 908254 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1214984 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0823. Min Act: -0.0000

Data Index: 274778 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0684. Min Act: -0.0000

Data Index: 684085 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1506999 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.1906. Min Act: -0.0000

Data Index: 1827518 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.1442. Min Act: -0.0000

Data Index: 1831859 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1675746 (The Pile)

Max Activating Token Index: 868

Text #11

Max Range: 1.7427. Min Range: -1.7427

Max Act: 0.9672. Min Act: -0.0000

Data Index: 696756 (The Pile)

Max Activating Token Index: 899

Text #12

Max Range: 1.7427. Min Range: -1.7427

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1752869 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 1.7427. Min Range: -1.7427

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1696026 (The Pile)

Max Activating Token Index: 482

Text #14

Max Range: 1.7427. Min Range: -1.7427

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1535179 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0170. Min Act: -0.0000

Data Index: 1600649 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1222667 (The Pile)

Max Activating Token Index: 775

Text #17

Max Range: 1.7427. Min Range: -1.7427

Max Act: 0.9832. Min Act: -0.0000

Data Index: 421555 (The Pile)

Max Activating Token Index: 823

Text #18

Max Range: 1.7427. Min Range: -1.7427

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1107308 (The Pile)

Max Activating Token Index: 731

Text #19

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.2897. Min Act: -0.0000

Data Index: 717727 (The Pile)

Max Activating Token Index: 496