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

Dataset: The Pile

Neuron 1768 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.4831. Min Act: -0.0000

Data Index: 1457736 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.6021. Min Act: -0.0000

Data Index: 1724755 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1931895 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.4256. Min Act: -0.0000

Data Index: 1524630 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.3441. Min Act: -0.0000

Data Index: 1961535 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1141275 (The Pile)

Max Activating Token Index: 785

Text #6

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.3296. Min Act: -0.0000

Data Index: 204283 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.3363. Min Act: -0.0000

Data Index: 1659194 (The Pile)

Max Activating Token Index: 400

Text #8

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.0164. Min Act: -0.0000

Data Index: 1087109 (The Pile)

Max Activating Token Index: 748

Text #9

Max Range: 1.6021. Min Range: -1.6021

Max Act: 0.9693. Min Act: -0.0000

Data Index: 742394 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.3219. Min Act: -0.0000

Data Index: 77994 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.3538. Min Act: -0.0000

Data Index: 15350 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.2635. Min Act: -0.0000

Data Index: 1970097 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1173623 (The Pile)

Max Activating Token Index: 9

Text #14

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.2513. Min Act: -0.0000

Data Index: 1599144 (The Pile)

Max Activating Token Index: 390

Text #15

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.2049. Min Act: -0.0000

Data Index: 1599665 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.2379. Min Act: -0.0000

Data Index: 28840 (The Pile)

Max Activating Token Index: 7

Text #17

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.2086. Min Act: -0.0000

Data Index: 1591347 (The Pile)

Max Activating Token Index: 504

Text #18

Max Range: 1.6021. Min Range: -1.6021

Max Act: 0.9456. Min Act: -0.0000

Data Index: 543462 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 1.6021. Min Range: -1.6021

Max Act: 1.2042. Min Act: -0.0000

Data Index: 1105547 (The Pile)

Max Activating Token Index: 154