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

Dataset: The Pile

Neuron 2275 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: 3.1242. Min Range: -3.1242

Max Act: 3.1242. Min Act: -0.0000

Data Index: 1527685 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 3.1242. Min Range: -3.1242

Max Act: 3.0853. Min Act: -0.0000

Data Index: 272985 (The Pile)

Max Activating Token Index: 454

Text #2

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.7641. Min Act: -0.0000

Data Index: 470947 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.6364. Min Act: -0.0000

Data Index: 1176751 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.3435. Min Act: -0.0000

Data Index: 1658129 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.1834. Min Act: -0.0000

Data Index: 750508 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.0041. Min Act: -0.0000

Data Index: 511051 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.8767. Min Act: -0.0000

Data Index: 311574 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.8810. Min Act: -0.0000

Data Index: 824273 (The Pile)

Max Activating Token Index: 1022

Text #9

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.7873. Min Act: -0.0000

Data Index: 496085 (The Pile)

Max Activating Token Index: 94

Text #10

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.8261. Min Act: -0.0000

Data Index: 1974615 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.9913. Min Act: -0.0000

Data Index: 1532324 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.9620. Min Act: -0.0000

Data Index: 197329 (The Pile)

Max Activating Token Index: 831

Text #13

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.6540. Min Act: -0.0000

Data Index: 1065812 (The Pile)

Max Activating Token Index: 856

Text #14

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.5345. Min Act: -0.0000

Data Index: 1416199 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.6591. Min Act: -0.0000

Data Index: 1759887 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.6437. Min Act: -0.0000

Data Index: 163565 (The Pile)

Max Activating Token Index: 820

Text #17

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.6367. Min Act: -0.0000

Data Index: 687364 (The Pile)

Max Activating Token Index: 70

Text #18

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.6132. Min Act: -0.0000

Data Index: 588386 (The Pile)

Max Activating Token Index: 138

Text #19

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.6666. Min Act: -0.0000

Data Index: 713224 (The Pile)

Max Activating Token Index: 819