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

Dataset: The Pile

Neuron 4240 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.6413. Min Act: -0.0000

Data Index: 1133797 (The Pile)

Max Activating Token Index: 712

Text #1

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.7533. Min Act: -0.0000

Data Index: 1442175 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.5333. Min Act: 0.0000

Data Index: 1536107 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.6024. Min Act: -0.0000

Data Index: 687065 (The Pile)

Max Activating Token Index: 234

Text #4

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.1549. Min Act: -0.0000

Data Index: 865846 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.1830. Min Act: -0.0000

Data Index: 1251622 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.0604. Min Act: -0.0000

Data Index: 1123383 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.0563. Min Act: -0.0000

Data Index: 898390 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.1655. Min Act: -0.0000

Data Index: 1631755 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 3.7533. Min Range: -3.7533

Max Act: 2.9306. Min Act: -0.0000

Data Index: 1263019 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.2340. Min Act: -0.0000

Data Index: 1748780 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.0766. Min Act: -0.0000

Data Index: 1183335 (The Pile)

Max Activating Token Index: 807

Text #12

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.3138. Min Act: -0.0000

Data Index: 1125831 (The Pile)

Max Activating Token Index: 381

Text #13

Max Range: 3.7533. Min Range: -3.7533

Max Act: 2.9792. Min Act: -0.0000

Data Index: 1699667 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 3.7533. Min Range: -3.7533

Max Act: 2.9752. Min Act: -0.0000

Data Index: 1085879 (The Pile)

Max Activating Token Index: 369

Text #15

Max Range: 3.7533. Min Range: -3.7533

Max Act: 2.9806. Min Act: -0.0000

Data Index: 289147 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 3.7533. Min Range: -3.7533

Max Act: 2.9817. Min Act: -0.0000

Data Index: 1319682 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 3.7533. Min Range: -3.7533

Max Act: 2.7313. Min Act: -0.0000

Data Index: 1593540 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 3.7533. Min Range: -3.7533

Max Act: 2.9358. Min Act: -0.0000

Data Index: 1931758 (The Pile)

Max Activating Token Index: 696

Text #19

Max Range: 3.7533. Min Range: -3.7533

Max Act: 3.0730. Min Act: -0.0000

Data Index: 469542 (The Pile)

Max Activating Token Index: 449