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

Dataset: The Pile

Neuron 2206 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0750. Min Range: -1.0750

Max Act: 1.0750. Min Act: -0.0000

Data Index: 674076 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1221132 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.8801. Min Act: -0.0000

Data Index: 126794 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1250097 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.8632. Min Act: -0.0000

Data Index: 824100 (The Pile)

Max Activating Token Index: 755

Text #5

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1800314 (The Pile)

Max Activating Token Index: 948

Text #6

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.8147. Min Act: -0.0000

Data Index: 685208 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7829. Min Act: -0.0000

Data Index: 715971 (The Pile)

Max Activating Token Index: 914

Text #8

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7864. Min Act: -0.0000

Data Index: 502422 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7955. Min Act: -0.0000

Data Index: 204456 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1897360 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7436. Min Act: -0.0000

Data Index: 795745 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7043. Min Act: -0.0000

Data Index: 1934630 (The Pile)

Max Activating Token Index: 870

Text #13

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1587823 (The Pile)

Max Activating Token Index: 783

Text #14

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6742. Min Act: -0.0000

Data Index: 633779 (The Pile)

Max Activating Token Index: 954

Text #15

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6807. Min Act: -0.0000

Data Index: 562908 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1886481 (The Pile)

Max Activating Token Index: 398

Text #17

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1670296 (The Pile)

Max Activating Token Index: 799

Text #18

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6586. Min Act: -0.0000

Data Index: 931531 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1970784 (The Pile)

Max Activating Token Index: 334