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

Dataset: The Pile

Neuron 258 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: 1.0137. Min Range: -1.0137

Max Act: 0.9991. Min Act: -0.0000

Data Index: 1822617 (The Pile)

Max Activating Token Index: 387

Text #1

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7856. Min Act: -0.0000

Data Index: 422408 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 1.0137. Min Range: -1.0137

Max Act: 1.0137. Min Act: -0.0000

Data Index: 421615 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7994. Min Act: -0.0000

Data Index: 1023719 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7665. Min Act: -0.0000

Data Index: 511210 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1845801 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1943031 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7374. Min Act: -0.0000

Data Index: 663745 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1712123 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.7673. Min Act: -0.0000

Data Index: 204971 (The Pile)

Max Activating Token Index: 96

Text #10

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1119029 (The Pile)

Max Activating Token Index: 550

Text #11

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.6239. Min Act: -0.0000

Data Index: 946325 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.6108. Min Act: -0.0000

Data Index: 966737 (The Pile)

Max Activating Token Index: 657

Text #13

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.5745. Min Act: -0.0000

Data Index: 871416 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1990673 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.4998. Min Act: -0.0000

Data Index: 70777 (The Pile)

Max Activating Token Index: 227

Text #16

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.4739. Min Act: -0.0000

Data Index: 826167 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1430544 (The Pile)

Max Activating Token Index: 1021

Text #18

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.5710. Min Act: -0.0000

Data Index: 67918 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 1.0137. Min Range: -1.0137

Max Act: 0.5139. Min Act: -0.0000

Data Index: 991088 (The Pile)

Max Activating Token Index: 38