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

Dataset: The Pile

Neuron 5040 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: 7.7003. Min Range: -7.7003

Max Act: 7.7003. Min Act: -0.0000

Data Index: 1047862 (The Pile)

Max Activating Token Index: 372

Text #1

Max Range: 7.7003. Min Range: -7.7003

Max Act: 7.2621. Min Act: -0.0000

Data Index: 1154347 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 7.7003. Min Range: -7.7003

Max Act: 7.2165. Min Act: -0.0000

Data Index: 1850074 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 7.7003. Min Range: -7.7003

Max Act: 7.2672. Min Act: -0.0000

Data Index: 356269 (The Pile)

Max Activating Token Index: 704

Text #4

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.6385. Min Act: -0.0000

Data Index: 890228 (The Pile)

Max Activating Token Index: 301

Text #5

Max Range: 7.7003. Min Range: -7.7003

Max Act: 7.0424. Min Act: -0.0000

Data Index: 1440334 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.9251. Min Act: -0.0000

Data Index: 526582 (The Pile)

Max Activating Token Index: 526

Text #7

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.6926. Min Act: -0.0000

Data Index: 839955 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 7.7003. Min Range: -7.7003

Max Act: 7.0546. Min Act: -0.0000

Data Index: 647415 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.9023. Min Act: -0.0000

Data Index: 1216338 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.4047. Min Act: -0.0000

Data Index: 1606577 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.9838. Min Act: -0.0000

Data Index: 1959532 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.6300. Min Act: -0.0000

Data Index: 772419 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.2963. Min Act: -0.0000

Data Index: 13748 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.7867. Min Act: -0.0000

Data Index: 1194152 (The Pile)

Max Activating Token Index: 740

Text #15

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.0177. Min Act: -0.0000

Data Index: 1832377 (The Pile)

Max Activating Token Index: 920

Text #16

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.5430. Min Act: -0.0000

Data Index: 1255774 (The Pile)

Max Activating Token Index: 843

Text #17

Max Range: 7.7003. Min Range: -7.7003

Max Act: 5.9862. Min Act: -0.0000

Data Index: 183212 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.6998. Min Act: -0.0000

Data Index: 1399700 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 7.7003. Min Range: -7.7003

Max Act: 6.4587. Min Act: -0.0000

Data Index: 1078721 (The Pile)

Max Activating Token Index: 717