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

Dataset: The Pile

Neuron 1446 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.9729. Min Act: -0.0000

Data Index: 388093 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1081699 (The Pile)

Max Activating Token Index: 464

Text #2

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7083. Min Act: -0.0000

Data Index: 976543 (The Pile)

Max Activating Token Index: 298

Text #3

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1114192 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.6277. Min Act: -0.0000

Data Index: 623512 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1172565 (The Pile)

Max Activating Token Index: 30

Text #6

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1054779 (The Pile)

Max Activating Token Index: 606

Text #7

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1588524 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1607981 (The Pile)

Max Activating Token Index: 940

Text #9

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1580366 (The Pile)

Max Activating Token Index: 342

Text #10

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1672978 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1144407 (The Pile)

Max Activating Token Index: 231

Text #12

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1387837 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.5479. Min Act: -0.0000

Data Index: 697562 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.5070. Min Act: -0.0000

Data Index: 914720 (The Pile)

Max Activating Token Index: 856

Text #15

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1583765 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.5044. Min Act: -0.0000

Data Index: 359919 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1592099 (The Pile)

Max Activating Token Index: 504

Text #18

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1832394 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.4664. Min Act: -0.0000

Data Index: 308938 (The Pile)

Max Activating Token Index: 382