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

Dataset: The Pile

Neuron 1581 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.6806. Min Act: 0.0000

Data Index: 366115 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.3833. Min Act: -0.0000

Data Index: 436725 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.0934. Min Act: -0.0000

Data Index: 420037 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.0541. Min Act: -0.0000

Data Index: 159816 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.9536. Min Act: -0.0000

Data Index: 1380250 (The Pile)

Max Activating Token Index: 952

Text #5

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1556925 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.8866. Min Act: -0.0000

Data Index: 813061 (The Pile)

Max Activating Token Index: 131

Text #7

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.9217. Min Act: 0.0000

Data Index: 1476385 (The Pile)

Max Activating Token Index: 978

Text #8

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.9401. Min Act: -0.0000

Data Index: 574038 (The Pile)

Max Activating Token Index: 324

Text #9

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1152840 (The Pile)

Max Activating Token Index: 873

Text #10

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.8933. Min Act: -0.0000

Data Index: 913593 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1247869 (The Pile)

Max Activating Token Index: 422

Text #12

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.8467. Min Act: -0.0000

Data Index: 887053 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1380871 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.8477. Min Act: -0.0000

Data Index: 288947 (The Pile)

Max Activating Token Index: 422

Text #15

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1428939 (The Pile)

Max Activating Token Index: 697

Text #16

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.8042. Min Act: -0.0000

Data Index: 488714 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.8059. Min Act: -0.0000

Data Index: 580671 (The Pile)

Max Activating Token Index: 360

Text #18

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.8377. Min Act: -0.0000

Data Index: 1442825 (The Pile)

Max Activating Token Index: 85

Text #19

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1788779 (The Pile)

Max Activating Token Index: 472