Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1914 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0289. Min Act: -0.0000

Data Index: 138753 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1073342 (The Pile)

Max Activating Token Index: 762

Text #2

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0065. Min Act: -0.0000

Data Index: 484194 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9412. Min Act: -0.0000

Data Index: 1074217 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1158263 (The Pile)

Max Activating Token Index: 454

Text #5

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1206353 (The Pile)

Max Activating Token Index: 549

Text #6

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.8865. Min Act: -0.0000

Data Index: 408615 (The Pile)

Max Activating Token Index: 751

Text #7

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9131. Min Act: -0.0000

Data Index: 507144 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1393215 (The Pile)

Max Activating Token Index: 883

Text #9

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9149. Min Act: -0.0000

Data Index: 978027 (The Pile)

Max Activating Token Index: 951

Text #10

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1628682 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1185964 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.9180. Min Act: -0.0000

Data Index: 496972 (The Pile)

Max Activating Token Index: 423

Text #13

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1737326 (The Pile)

Max Activating Token Index: 106

Text #14

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1375239 (The Pile)

Max Activating Token Index: 394

Text #15

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.7920. Min Act: -0.0000

Data Index: 1051723 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.8600. Min Act: -0.0000

Data Index: 994919 (The Pile)

Max Activating Token Index: 887

Text #17

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.8425. Min Act: -0.0000

Data Index: 283478 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1637774 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 1.1968. Min Range: -1.1968

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1898784 (The Pile)

Max Activating Token Index: 907