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

Dataset: The Pile

Neuron 3607 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: 1.1899. Min Range: -1.1899

Max Act: 1.1899. Min Act: -0.0000

Data Index: 551658 (The Pile)

Max Activating Token Index: 732

Text #1

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1651. Min Act: -0.0001

Data Index: 1180826 (The Pile)

Max Activating Token Index: 228

Text #2

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1570. Min Act: -0.0000

Data Index: 1419289 (The Pile)

Max Activating Token Index: 382

Text #3

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1616. Min Act: -0.0001

Data Index: 843002 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1426841 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0365. Min Act: -0.0000

Data Index: 1764217 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1348. Min Act: -0.0000

Data Index: 6232 (The Pile)

Max Activating Token Index: 360

Text #7

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0894. Min Act: -0.0000

Data Index: 646519 (The Pile)

Max Activating Token Index: 129

Text #8

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0222. Min Act: -0.0000

Data Index: 1715502 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0525. Min Act: -0.0000

Data Index: 291020 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1487864 (The Pile)

Max Activating Token Index: 396

Text #11

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0838. Min Act: -0.0000

Data Index: 1587941 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0130. Min Act: -0.0000

Data Index: 1498992 (The Pile)

Max Activating Token Index: 637

Text #13

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1338525 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.9556. Min Act: -0.0000

Data Index: 1633143 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0921. Min Act: -0.0000

Data Index: 1596546 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.9997. Min Act: -0.0000

Data Index: 1195344 (The Pile)

Max Activating Token Index: 423

Text #17

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0233. Min Act: -0.0000

Data Index: 43767 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.9899. Min Act: -0.0000

Data Index: 1479696 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0456. Min Act: -0.0000

Data Index: 133460 (The Pile)

Max Activating Token Index: 161