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

Dataset: The Pile

Neuron 1015 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.6188. Min Act: -0.0000

Data Index: 797679 (The Pile)

Max Activating Token Index: 63

Text #1

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.6673. Min Act: -0.0000

Data Index: 378860 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.6137. Min Act: -0.0000

Data Index: 135988 (The Pile)

Max Activating Token Index: 487

Text #3

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.5803. Min Act: -0.0000

Data Index: 1000058 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.6645. Min Act: -0.0000

Data Index: 1737526 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.6107. Min Act: -0.0000

Data Index: 1323900 (The Pile)

Max Activating Token Index: 52

Text #6

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.6542. Min Act: -0.0000

Data Index: 1148929 (The Pile)

Max Activating Token Index: 64

Text #7

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.6445. Min Act: -0.0000

Data Index: 1948676 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.4088. Min Act: -0.0000

Data Index: 1672033 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.1728. Min Act: -0.0000

Data Index: 665249 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.4409. Min Act: -0.0000

Data Index: 785744 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.3048. Min Act: -0.0000

Data Index: 1224608 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.5991. Min Act: -0.0000

Data Index: 1692405 (The Pile)

Max Activating Token Index: 43

Text #13

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.3563. Min Act: -0.0000

Data Index: 1707026 (The Pile)

Max Activating Token Index: 7

Text #14

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.1913. Min Act: -0.0000

Data Index: 945396 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.5018. Min Act: -0.0000

Data Index: 89611 (The Pile)

Max Activating Token Index: 9

Text #16

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.3183. Min Act: -0.0000

Data Index: 1954448 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.3481. Min Act: -0.0000

Data Index: 802995 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.1497. Min Act: -0.0000

Data Index: 698683 (The Pile)

Max Activating Token Index: 5

Text #19

Max Range: 3.6673. Min Range: -3.6673

Max Act: 3.4596. Min Act: -0.0000

Data Index: 667284 (The Pile)

Max Activating Token Index: 59