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

Dataset: The Pile

Neuron 3240 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: 0.5166. Min Range: -0.5166

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1787426 (The Pile)

Max Activating Token Index: 740

Text #1

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1229363 (The Pile)

Max Activating Token Index: 739

Text #2

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1209315 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4092. Min Act: -0.0000

Data Index: 424952 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4031. Min Act: -0.0000

Data Index: 573425 (The Pile)

Max Activating Token Index: 786

Text #5

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3774. Min Act: -0.0000

Data Index: 196588 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4440. Min Act: -0.0000

Data Index: 329917 (The Pile)

Max Activating Token Index: 968

Text #7

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3825. Min Act: -0.0000

Data Index: 82640 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3583. Min Act: -0.0000

Data Index: 670575 (The Pile)

Max Activating Token Index: 784

Text #9

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3107. Min Act: -0.0000

Data Index: 575248 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1906387 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1393686 (The Pile)

Max Activating Token Index: 935

Text #12

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3137. Min Act: -0.0000

Data Index: 158183 (The Pile)

Max Activating Token Index: 583

Text #13

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1624786 (The Pile)

Max Activating Token Index: 353

Text #14

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1323671 (The Pile)

Max Activating Token Index: 641

Text #15

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1284561 (The Pile)

Max Activating Token Index: 951

Text #16

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1008585 (The Pile)

Max Activating Token Index: 868

Text #17

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3194. Min Act: -0.0000

Data Index: 80071 (The Pile)

Max Activating Token Index: 401

Text #18

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1550395 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1322820 (The Pile)

Max Activating Token Index: 834