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

Dataset: The Pile

Neuron 642 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 13.9124. Min Range: -13.9124

Max Act: 13.9124. Min Act: -0.0000

Data Index: 883873 (The Pile)

Max Activating Token Index: 98

Text #1

Max Range: 13.9124. Min Range: -13.9124

Max Act: 13.1609. Min Act: -0.0000

Data Index: 1973636 (The Pile)

Max Activating Token Index: 44

Text #2

Max Range: 13.9124. Min Range: -13.9124

Max Act: 13.0781. Min Act: -0.0000

Data Index: 441308 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 13.9124. Min Range: -13.9124

Max Act: 13.1273. Min Act: -0.0000

Data Index: 934356 (The Pile)

Max Activating Token Index: 750

Text #4

Max Range: 13.9124. Min Range: -13.9124

Max Act: 13.0444. Min Act: -0.0000

Data Index: 769523 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.7652. Min Act: -0.0000

Data Index: 1167755 (The Pile)

Max Activating Token Index: 892

Text #6

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.4871. Min Act: -0.0000

Data Index: 389120 (The Pile)

Max Activating Token Index: 910

Text #7

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.4289. Min Act: -0.0000

Data Index: 1425831 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.7990. Min Act: -0.0000

Data Index: 1766030 (The Pile)

Max Activating Token Index: 89

Text #9

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.6944. Min Act: -0.0000

Data Index: 1978743 (The Pile)

Max Activating Token Index: 643

Text #10

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.3580. Min Act: -0.0000

Data Index: 1623094 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.4135. Min Act: -0.0000

Data Index: 763086 (The Pile)

Max Activating Token Index: 666

Text #12

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.2916. Min Act: -0.0000

Data Index: 813711 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.2753. Min Act: -0.0000

Data Index: 791053 (The Pile)

Max Activating Token Index: 283

Text #14

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.2762. Min Act: -0.0000

Data Index: 464995 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 13.9124. Min Range: -13.9124

Max Act: 11.8098. Min Act: -0.0000

Data Index: 910203 (The Pile)

Max Activating Token Index: 888

Text #16

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.7043. Min Act: -0.0000

Data Index: 136554 (The Pile)

Max Activating Token Index: 767

Text #17

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.5966. Min Act: -0.0000

Data Index: 681836 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.2638. Min Act: -0.0000

Data Index: 1229640 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 13.9124. Min Range: -13.9124

Max Act: 12.1589. Min Act: -0.0000

Data Index: 827161 (The Pile)

Max Activating Token Index: 353