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

Dataset: The Pile

Neuron 3765 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1932244 (The Pile)

Max Activating Token Index: 920

Text #1

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1424804 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1827772 (The Pile)

Max Activating Token Index: 412

Text #3

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1661906 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6494. Min Act: -0.0000

Data Index: 720986 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6788. Min Act: -0.0000

Data Index: 989567 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1151716 (The Pile)

Max Activating Token Index: 644

Text #7

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6603. Min Act: -0.0000

Data Index: 1174371 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1305653 (The Pile)

Max Activating Token Index: 314

Text #9

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7276. Min Act: -0.0000

Data Index: 322742 (The Pile)

Max Activating Token Index: 812

Text #10

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.5798. Min Act: -0.0000

Data Index: 80093 (The Pile)

Max Activating Token Index: 672

Text #11

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1345051 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6597. Min Act: -0.0000

Data Index: 756025 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6090. Min Act: -0.0000

Data Index: 466255 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1450770 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6124. Min Act: -0.0000

Data Index: 869920 (The Pile)

Max Activating Token Index: 820

Text #16

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.5899. Min Act: -0.0000

Data Index: 983747 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1876503 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.5524. Min Act: -0.0000

Data Index: 660427 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1109041 (The Pile)

Max Activating Token Index: 918