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

Dataset: The Pile

Neuron 3633 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 7.3459. Min Range: -7.3459

Max Act: 7.3459. Min Act: 0.0001

Data Index: 1457932 (The Pile)

Max Activating Token Index: 1000

Text #1

Max Range: 7.3459. Min Range: -7.3459

Max Act: 6.5471. Min Act: -0.0000

Data Index: 1206323 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 7.3459. Min Range: -7.3459

Max Act: 6.5656. Min Act: -0.0000

Data Index: 175640 (The Pile)

Max Activating Token Index: 496

Text #3

Max Range: 7.3459. Min Range: -7.3459

Max Act: 6.3827. Min Act: -0.0000

Data Index: 852945 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 7.3459. Min Range: -7.3459

Max Act: 6.6111. Min Act: -0.0000

Data Index: 1619962 (The Pile)

Max Activating Token Index: 89

Text #5

Max Range: 7.3459. Min Range: -7.3459

Max Act: 6.3294. Min Act: -0.0000

Data Index: 280881 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 7.3459. Min Range: -7.3459

Max Act: 6.2717. Min Act: -0.0000

Data Index: 1144463 (The Pile)

Max Activating Token Index: 531

Text #7

Max Range: 7.3459. Min Range: -7.3459

Max Act: 5.8534. Min Act: 0.0001

Data Index: 1501411 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 7.3459. Min Range: -7.3459

Max Act: 5.5272. Min Act: 0.0001

Data Index: 232319 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 7.3459. Min Range: -7.3459

Max Act: 5.2948. Min Act: 0.0000

Data Index: 720976 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 7.3459. Min Range: -7.3459

Max Act: 6.0256. Min Act: -0.0000

Data Index: 1017011 (The Pile)

Max Activating Token Index: 609

Text #11

Max Range: 7.3459. Min Range: -7.3459

Max Act: 5.4856. Min Act: -0.0000

Data Index: 1139079 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 7.3459. Min Range: -7.3459

Max Act: 5.3405. Min Act: -0.0000

Data Index: 1581293 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 7.3459. Min Range: -7.3459

Max Act: 5.5422. Min Act: -0.0000

Data Index: 584854 (The Pile)

Max Activating Token Index: 157

Text #14

Max Range: 7.3459. Min Range: -7.3459

Max Act: 5.7230. Min Act: -0.0000

Data Index: 1355132 (The Pile)

Max Activating Token Index: 282

Text #15

Max Range: 7.3459. Min Range: -7.3459

Max Act: 5.2481. Min Act: -0.0000

Data Index: 1804743 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 7.3459. Min Range: -7.3459

Max Act: 5.2534. Min Act: 0.0001

Data Index: 879311 (The Pile)

Max Activating Token Index: 833

Text #17

Max Range: 7.3459. Min Range: -7.3459

Max Act: 5.2040. Min Act: -0.0000

Data Index: 443502 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 7.3459. Min Range: -7.3459

Max Act: 4.9267. Min Act: 0.0000

Data Index: 1703988 (The Pile)

Max Activating Token Index: 212

Text #19

Max Range: 7.3459. Min Range: -7.3459

Max Act: 4.8118. Min Act: -0.0000

Data Index: 106153 (The Pile)

Max Activating Token Index: 608