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

Dataset: The Pile

Neuron 3681 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: 3.6846. Min Range: -3.6846

Max Act: 3.6846. Min Act: -0.0000

Data Index: 1679424 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6094. Min Act: -0.0000

Data Index: 1843183 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.2371. Min Act: -0.0000

Data Index: 15846 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.0540. Min Act: -0.0000

Data Index: 876668 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.6225. Min Act: -0.0000

Data Index: 1921845 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.4310. Min Act: -0.0000

Data Index: 1181496 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.3114. Min Act: -0.0000

Data Index: 1807014 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.3185. Min Act: -0.0000

Data Index: 1809400 (The Pile)

Max Activating Token Index: 790

Text #8

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.1061. Min Act: -0.0000

Data Index: 685916 (The Pile)

Max Activating Token Index: 539

Text #9

Max Range: 3.6846. Min Range: -3.6846

Max Act: 2.9305. Min Act: -0.0000

Data Index: 757120 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.0520. Min Act: -0.0000

Data Index: 120336 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 3.6846. Min Range: -3.6846

Max Act: 2.6615. Min Act: -0.0000

Data Index: 711450 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.0594. Min Act: -0.0000

Data Index: 211422 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 3.6846. Min Range: -3.6846

Max Act: 2.7452. Min Act: -0.0000

Data Index: 1292143 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 3.6846. Min Range: -3.6846

Max Act: 2.8810. Min Act: -0.0000

Data Index: 1701352 (The Pile)

Max Activating Token Index: 489

Text #15

Max Range: 3.6846. Min Range: -3.6846

Max Act: 2.9886. Min Act: -0.0000

Data Index: 1546118 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 3.6846. Min Range: -3.6846

Max Act: 3.0782. Min Act: -0.0000

Data Index: 1069968 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 3.6846. Min Range: -3.6846

Max Act: 2.8139. Min Act: -0.0000

Data Index: 1907239 (The Pile)

Max Activating Token Index: 771

Text #18

Max Range: 3.6846. Min Range: -3.6846

Max Act: 2.5412. Min Act: -0.0000

Data Index: 11308 (The Pile)

Max Activating Token Index: 99

Text #19

Max Range: 3.6846. Min Range: -3.6846

Max Act: 2.8685. Min Act: -0.0000

Data Index: 1968987 (The Pile)

Max Activating Token Index: 384