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

Dataset: The Pile

Neuron 62 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: 3.9633. Min Range: -3.9633

Max Act: 3.7107. Min Act: -0.0000

Data Index: 121716 (The Pile)

Max Activating Token Index: 902

Text #1

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.8735. Min Act: -0.0000

Data Index: 816597 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.8466. Min Act: -0.0000

Data Index: 1535325 (The Pile)

Max Activating Token Index: 369

Text #3

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.9633. Min Act: -0.0000

Data Index: 345454 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.9269. Min Act: -0.0000

Data Index: 1787689 (The Pile)

Max Activating Token Index: 677

Text #5

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.8837. Min Act: -0.0000

Data Index: 309414 (The Pile)

Max Activating Token Index: 752

Text #6

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.7044. Min Act: -0.0000

Data Index: 1059295 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.8661. Min Act: -0.0000

Data Index: 1385351 (The Pile)

Max Activating Token Index: 284

Text #8

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.8937. Min Act: -0.0000

Data Index: 1138902 (The Pile)

Max Activating Token Index: 608

Text #9

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.8515. Min Act: -0.0000

Data Index: 1819034 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.8213. Min Act: -0.0001

Data Index: 585695 (The Pile)

Max Activating Token Index: 756

Text #11

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.8306. Min Act: -0.0000

Data Index: 197305 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.6642. Min Act: -0.0000

Data Index: 585063 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.6827. Min Act: -0.0000

Data Index: 133367 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.6592. Min Act: -0.0000

Data Index: 87417 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.8049. Min Act: -0.0000

Data Index: 1498275 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.6311. Min Act: -0.0000

Data Index: 1017197 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.9426. Min Act: -0.0000

Data Index: 220965 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.6191. Min Act: -0.0000

Data Index: 334350 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 3.9633. Min Range: -3.9633

Max Act: 3.6227. Min Act: -0.0000

Data Index: 1480048 (The Pile)

Max Activating Token Index: 770