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

Dataset: The Pile

Neuron 904 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: 1.1030. Min Range: -1.1030

Max Act: 1.1030. Min Act: -0.0000

Data Index: 774004 (The Pile)

Max Activating Token Index: 480

Text #1

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0213. Min Act: -0.0000

Data Index: 1444055 (The Pile)

Max Activating Token Index: 837

Text #2

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1100126 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9962. Min Act: -0.0000

Data Index: 924039 (The Pile)

Max Activating Token Index: 355

Text #4

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9975. Min Act: -0.0000

Data Index: 347096 (The Pile)

Max Activating Token Index: 477

Text #5

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1831592 (The Pile)

Max Activating Token Index: 173

Text #6

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1500887 (The Pile)

Max Activating Token Index: 805

Text #7

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1980294 (The Pile)

Max Activating Token Index: 577

Text #8

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1449199 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1395251 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8844. Min Act: -0.0000

Data Index: 684798 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1071433 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8175. Min Act: -0.0000

Data Index: 584044 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1541757 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7708. Min Act: -0.0000

Data Index: 791857 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8023. Min Act: -0.0000

Data Index: 279304 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1259812 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1136688 (The Pile)

Max Activating Token Index: 992

Text #18

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1421760 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1410721 (The Pile)

Max Activating Token Index: 857