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

Dataset: The Pile

Neuron 1921 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: 0.8523. Min Range: -0.8523

Max Act: 0.8523. Min Act: -0.0000

Data Index: 314087 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7238. Min Act: -0.0000

Data Index: 235963 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5977. Min Act: -0.0000

Data Index: 335650 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1894298 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5111. Min Act: -0.0000

Data Index: 563552 (The Pile)

Max Activating Token Index: 727

Text #5

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5676. Min Act: -0.0000

Data Index: 644960 (The Pile)

Max Activating Token Index: 865

Text #6

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5365. Min Act: -0.0000

Data Index: 466183 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1092083 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5276. Min Act: -0.0000

Data Index: 732036 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1749786 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.4826. Min Act: -0.0000

Data Index: 732125 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1730617 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1122436 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1344070 (The Pile)

Max Activating Token Index: 485

Text #14

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.4942. Min Act: -0.0000

Data Index: 246309 (The Pile)

Max Activating Token Index: 658

Text #15

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5041. Min Act: -0.0000

Data Index: 116864 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5097. Min Act: -0.0000

Data Index: 706008 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.4853. Min Act: -0.0000

Data Index: 281804 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.4799. Min Act: -0.0000

Data Index: 784674 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.4910. Min Act: -0.0000

Data Index: 27454 (The Pile)

Max Activating Token Index: 516