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

Dataset: The Pile

Neuron 1680 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: 1.0218. Min Range: -1.0218

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1164466 (The Pile)

Max Activating Token Index: 856

Text #1

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1168585 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.9402. Min Act: -0.0000

Data Index: 205559 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1788522 (The Pile)

Max Activating Token Index: 112

Text #4

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1135328 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.9155. Min Act: -0.0000

Data Index: 1377502 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1954094 (The Pile)

Max Activating Token Index: 379

Text #7

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8393. Min Act: -0.0000

Data Index: 512331 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1839690 (The Pile)

Max Activating Token Index: 886

Text #9

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1923102 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8185. Min Act: -0.0000

Data Index: 559787 (The Pile)

Max Activating Token Index: 411

Text #11

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8115. Min Act: -0.0000

Data Index: 776825 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.7272. Min Act: -0.0000

Data Index: 626796 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1662829 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1790468 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1599459 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1997302 (The Pile)

Max Activating Token Index: 103

Text #17

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1308362 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.7447. Min Act: -0.0000

Data Index: 1421202 (The Pile)

Max Activating Token Index: 739

Text #19

Max Range: 1.0218. Min Range: -1.0218

Max Act: 0.7116. Min Act: -0.0000

Data Index: 147144 (The Pile)

Max Activating Token Index: 776