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

Dataset: The Pile

Neuron 3225 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.7818. Min Act: -0.0000

Data Index: 1591285 (The Pile)

Max Activating Token Index: 439

Text #1

Max Range: 3.0014. Min Range: -3.0014

Max Act: 3.0014. Min Act: -0.0000

Data Index: 1961538 (The Pile)

Max Activating Token Index: 321

Text #2

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.6628. Min Act: -0.0000

Data Index: 1418351 (The Pile)

Max Activating Token Index: 770

Text #3

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.5436. Min Act: -0.0000

Data Index: 1205681 (The Pile)

Max Activating Token Index: 559

Text #4

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.2014. Min Act: -0.0000

Data Index: 1275151 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.1589. Min Act: -0.0000

Data Index: 46605 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.1283. Min Act: -0.0000

Data Index: 1011207 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.2075. Min Act: -0.0000

Data Index: 36109 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.1501. Min Act: -0.0000

Data Index: 370999 (The Pile)

Max Activating Token Index: 65

Text #9

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.2515. Min Act: -0.0000

Data Index: 267226 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.3755. Min Act: -0.0000

Data Index: 543112 (The Pile)

Max Activating Token Index: 112

Text #11

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.0369. Min Act: -0.0000

Data Index: 1854016 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.1284. Min Act: -0.0000

Data Index: 1405213 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.0426. Min Act: -0.0000

Data Index: 911285 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.0380. Min Act: -0.0000

Data Index: 1662838 (The Pile)

Max Activating Token Index: 110

Text #15

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.0292. Min Act: -0.0000

Data Index: 1443531 (The Pile)

Max Activating Token Index: 565

Text #16

Max Range: 3.0014. Min Range: -3.0014

Max Act: 1.7027. Min Act: -0.0000

Data Index: 210068 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 3.0014. Min Range: -3.0014

Max Act: 1.8901. Min Act: -0.0000

Data Index: 1992327 (The Pile)

Max Activating Token Index: 707

Text #18

Max Range: 3.0014. Min Range: -3.0014

Max Act: 1.9872. Min Act: -0.0000

Data Index: 22416 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 3.0014. Min Range: -3.0014

Max Act: 1.9789. Min Act: -0.0000

Data Index: 1290289 (The Pile)

Max Activating Token Index: 13