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

Dataset: The Pile

Neuron 1148 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: 3.0547. Min Range: -3.0547

Max Act: 3.0547. Min Act: -0.0000

Data Index: 691650 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.2220. Min Act: -0.0000

Data Index: 834268 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.1741. Min Act: -0.0000

Data Index: 99310 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.0814. Min Act: -0.0000

Data Index: 725963 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.9597. Min Act: -0.0000

Data Index: 1054919 (The Pile)

Max Activating Token Index: 168

Text #5

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.0397. Min Act: -0.0000

Data Index: 1981350 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.8872. Min Act: -0.0000

Data Index: 1754258 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.9928. Min Act: -0.0000

Data Index: 97383 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.9787. Min Act: -0.0000

Data Index: 774324 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.8373. Min Act: -0.0000

Data Index: 10393 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 3.0547. Min Range: -3.0547

Max Act: 2.0346. Min Act: -0.0000

Data Index: 1985674 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.8199. Min Act: -0.0000

Data Index: 184947 (The Pile)

Max Activating Token Index: 327

Text #12

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.8161. Min Act: -0.0000

Data Index: 621528 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.9023. Min Act: -0.0000

Data Index: 576623 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.9074. Min Act: -0.0000

Data Index: 1999327 (The Pile)

Max Activating Token Index: 838

Text #15

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.7837. Min Act: -0.0000

Data Index: 491832 (The Pile)

Max Activating Token Index: 15

Text #16

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.7922. Min Act: -0.0000

Data Index: 289951 (The Pile)

Max Activating Token Index: 340

Text #17

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.7775. Min Act: -0.0000

Data Index: 1594382 (The Pile)

Max Activating Token Index: 898

Text #18

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.8651. Min Act: -0.0000

Data Index: 1223152 (The Pile)

Max Activating Token Index: 323

Text #19

Max Range: 3.0547. Min Range: -3.0547

Max Act: 1.9587. Min Act: -0.0000

Data Index: 1824017 (The Pile)

Max Activating Token Index: 125