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

Dataset: The Pile

Neuron 2937 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.5027. Min Act: -0.0000

Data Index: 54885 (The Pile)

Max Activating Token Index: 464

Text #1

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4863. Min Act: -0.0000

Data Index: 93738 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1046671 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4801. Min Act: -0.0000

Data Index: 415421 (The Pile)

Max Activating Token Index: 690

Text #4

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4786. Min Act: -0.0000

Data Index: 820108 (The Pile)

Max Activating Token Index: 434

Text #5

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1669349 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4620. Min Act: -0.0000

Data Index: 606159 (The Pile)

Max Activating Token Index: 444

Text #7

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4718. Min Act: -0.0000

Data Index: 943639 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1566433 (The Pile)

Max Activating Token Index: 907

Text #9

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1672112 (The Pile)

Max Activating Token Index: 546

Text #10

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1956992 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4092. Min Act: -0.0000

Data Index: 496130 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4208. Min Act: -0.0000

Data Index: 880318 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1353815 (The Pile)

Max Activating Token Index: 910

Text #14

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1366513 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3970. Min Act: -0.0000

Data Index: 812396 (The Pile)

Max Activating Token Index: 529

Text #16

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4188. Min Act: -0.0000

Data Index: 382657 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1683241 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4000. Min Act: -0.0000

Data Index: 827662 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3870. Min Act: -0.0000

Data Index: 557226 (The Pile)

Max Activating Token Index: 782