Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2343 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1945. Min Act: -0.0001
Data Index: 749092 (The Pile)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.2021. Min Act: -0.0001
Data Index: 1507725 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.2155. Min Act: -0.0001
Data Index: 641194 (The Pile)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1922. Min Act: -0.0001
Data Index: 1986880 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1920. Min Act: -0.0001
Data Index: 682507 (The Pile)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1837. Min Act: -0.0001
Data Index: 161155 (The Pile)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1885. Min Act: -0.0001
Data Index: 977842 (The Pile)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1678. Min Act: -0.0001
Data Index: 236110 (The Pile)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.2008. Min Act: -0.0001
Data Index: 560745 (The Pile)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1928. Min Act: -0.0001
Data Index: 1837320 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1753. Min Act: -0.0001
Data Index: 758785 (The Pile)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.2038. Min Act: -0.0001
Data Index: 922637 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1622. Min Act: -0.0001
Data Index: 1174694 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1710. Min Act: -0.0001
Data Index: 607017 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1823. Min Act: -0.0001
Data Index: 191087 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1733. Min Act: -0.0001
Data Index: 529544 (The Pile)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1728. Min Act: -0.0001
Data Index: 910631 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1517. Min Act: -0.0001
Data Index: 1604793 (The Pile)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1824. Min Act: -0.0001
Data Index: 1187358 (The Pile)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2155. Min Range: -0.2155
Max Act: 0.1331. Min Act: -0.0001
Data Index: 1976738 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19