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

Dataset: The Pile

Neuron 778 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1092829 (The Pile)

Max Activating Token Index: 343

Text #1

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1461986 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6121. Min Act: -0.0000

Data Index: 339464 (The Pile)

Max Activating Token Index: 352

Text #3

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1963357 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1422818 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6107. Min Act: -0.0000

Data Index: 434579 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1031959 (The Pile)

Max Activating Token Index: 387

Text #7

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1834621 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5259. Min Act: -0.0000

Data Index: 793865 (The Pile)

Max Activating Token Index: 661

Text #9

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5144. Min Act: -0.0000

Data Index: 437003 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4815. Min Act: -0.0000

Data Index: 643369 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5446. Min Act: -0.0000

Data Index: 718394 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4962. Min Act: -0.0000

Data Index: 576566 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4938. Min Act: -0.0000

Data Index: 701689 (The Pile)

Max Activating Token Index: 968

Text #14

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4763. Min Act: -0.0000

Data Index: 663240 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4888. Min Act: -0.0000

Data Index: 539625 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4615. Min Act: -0.0000

Data Index: 277859 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1915761 (The Pile)

Max Activating Token Index: 102

Text #18

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1538419 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1252025 (The Pile)

Max Activating Token Index: 874