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

Dataset: The Pile

Neuron 310 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: 1.8999. Min Range: -1.8999

Max Act: 1.7426. Min Act: -0.0000

Data Index: 1008209 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.8999. Min Act: -0.0000

Data Index: 1928938 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.6720. Min Act: -0.0000

Data Index: 596267 (The Pile)

Max Activating Token Index: 199

Text #3

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.6406. Min Act: -0.0000

Data Index: 1771479 (The Pile)

Max Activating Token Index: 780

Text #4

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.7097. Min Act: -0.0000

Data Index: 349900 (The Pile)

Max Activating Token Index: 128

Text #5

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.6152. Min Act: -0.0000

Data Index: 1214559 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.4577. Min Act: -0.0000

Data Index: 784290 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.6612. Min Act: -0.0000

Data Index: 350852 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.6099. Min Act: -0.0000

Data Index: 1837006 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.4678. Min Act: -0.0000

Data Index: 1249768 (The Pile)

Max Activating Token Index: 745

Text #10

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.7334. Min Act: -0.0000

Data Index: 1516657 (The Pile)

Max Activating Token Index: 168

Text #11

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.4662. Min Act: -0.0000

Data Index: 654344 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.4319. Min Act: -0.0000

Data Index: 537284 (The Pile)

Max Activating Token Index: 97

Text #13

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.4129. Min Act: -0.0000

Data Index: 507110 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.3309. Min Act: -0.0000

Data Index: 1460830 (The Pile)

Max Activating Token Index: 755

Text #15

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.4023. Min Act: -0.0000

Data Index: 799056 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1126108 (The Pile)

Max Activating Token Index: 799

Text #17

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.3809. Min Act: -0.0000

Data Index: 802498 (The Pile)

Max Activating Token Index: 31

Text #18

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.3213. Min Act: -0.0000

Data Index: 1555155 (The Pile)

Max Activating Token Index: 154

Text #19

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.3623. Min Act: -0.0000

Data Index: 395031 (The Pile)

Max Activating Token Index: 835