Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 73 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.5232. Min Act: -0.0000

Data Index: 392987 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.2801. Min Act: -0.0000

Data Index: 956674 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.2373. Min Act: -0.0000

Data Index: 1390720 (The Pile)

Max Activating Token Index: 327

Text #3

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.2914. Min Act: -0.0000

Data Index: 271961 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.2712. Min Act: -0.0000

Data Index: 511920 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.2111. Min Act: -0.0000

Data Index: 1685150 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.1789. Min Act: -0.0000

Data Index: 457423 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.1291. Min Act: -0.0000

Data Index: 5515 (The Pile)

Max Activating Token Index: 304

Text #8

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0970. Min Act: -0.0000

Data Index: 908598 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1327642 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0508. Min Act: -0.0000

Data Index: 890283 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.1051. Min Act: -0.0000

Data Index: 976936 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1213465 (The Pile)

Max Activating Token Index: 476

Text #13

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1340709 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0310. Min Act: -0.0000

Data Index: 845405 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1323973 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0624. Min Act: -0.0000

Data Index: 1157974 (The Pile)

Max Activating Token Index: 564

Text #17

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0422. Min Act: -0.0000

Data Index: 1213430 (The Pile)

Max Activating Token Index: 203

Text #18

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0350. Min Act: -0.0000

Data Index: 631320 (The Pile)

Max Activating Token Index: 322

Text #19

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9823. Min Act: -0.0000

Data Index: 47853 (The Pile)

Max Activating Token Index: 266