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

Dataset: The Pile

Neuron 736 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.8031. Min Act: -0.0000

Data Index: 1494764 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 8.1280. Min Range: -8.1280

Max Act: 8.1280. Min Act: -0.0000

Data Index: 403542 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.4918. Min Act: -0.0000

Data Index: 1675830 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.0840. Min Act: -0.0000

Data Index: 1744806 (The Pile)

Max Activating Token Index: 990

Text #4

Max Range: 8.1280. Min Range: -8.1280

Max Act: 6.4115. Min Act: -0.0000

Data Index: 1540758 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 8.1280. Min Range: -8.1280

Max Act: 6.8176. Min Act: -0.0000

Data Index: 1709642 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 8.1280. Min Range: -8.1280

Max Act: 6.3090. Min Act: -0.0000

Data Index: 1658612 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 8.1280. Min Range: -8.1280

Max Act: 6.6622. Min Act: -0.0000

Data Index: 1341797 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.1352. Min Act: -0.0000

Data Index: 384309 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 8.1280. Min Range: -8.1280

Max Act: 6.1904. Min Act: -0.0000

Data Index: 975257 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 8.1280. Min Range: -8.1280

Max Act: 6.3108. Min Act: -0.0000

Data Index: 652891 (The Pile)

Max Activating Token Index: 755

Text #11

Max Range: 8.1280. Min Range: -8.1280

Max Act: 6.0512. Min Act: -0.0000

Data Index: 222519 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 8.1280. Min Range: -8.1280

Max Act: 6.5807. Min Act: -0.0000

Data Index: 904099 (The Pile)

Max Activating Token Index: 50

Text #13

Max Range: 8.1280. Min Range: -8.1280

Max Act: 5.8126. Min Act: -0.0000

Data Index: 1804709 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 8.1280. Min Range: -8.1280

Max Act: 5.9186. Min Act: -0.0000

Data Index: 475552 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 8.1280. Min Range: -8.1280

Max Act: 5.8708. Min Act: -0.0000

Data Index: 742030 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 8.1280. Min Range: -8.1280

Max Act: 6.0075. Min Act: -0.0000

Data Index: 321120 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 8.1280. Min Range: -8.1280

Max Act: 6.3163. Min Act: -0.0000

Data Index: 480383 (The Pile)

Max Activating Token Index: 116

Text #18

Max Range: 8.1280. Min Range: -8.1280

Max Act: 5.6854. Min Act: -0.0000

Data Index: 844963 (The Pile)

Max Activating Token Index: 797

Text #19

Max Range: 8.1280. Min Range: -8.1280

Max Act: 5.8691. Min Act: -0.0000

Data Index: 94967 (The Pile)

Max Activating Token Index: 507