Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4083 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1817. Min Act: -0.0002
Data Index: 828769 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1751. Min Act: -0.0001
Data Index: 1426146 (Python Code)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1889. Min Act: -0.0001
Data Index: 1320431 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1841. Min Act: -0.0001
Data Index: 1509810 (Python Code)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1801. Min Act: -0.0001
Data Index: 1240310 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1780. Min Act: -0.0001
Data Index: 786388 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1681. Min Act: -0.0001
Data Index: 1499715 (Python Code)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1665. Min Act: -0.0002
Data Index: 740094 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1536. Min Act: -0.0002
Data Index: 327655 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1654. Min Act: -0.0001
Data Index: 336970 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1430. Min Act: -0.0001
Data Index: 1519300 (Python Code)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1667. Min Act: -0.0002
Data Index: 335999 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1744. Min Act: -0.0001
Data Index: 1625622 (Python Code)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1535. Min Act: -0.0001
Data Index: 1575176 (Python Code)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1400. Min Act: -0.0001
Data Index: 1590984 (Python Code)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1653. Min Act: -0.0001
Data Index: 795373 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1590. Min Act: -0.0001
Data Index: 1619774 (Python Code)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1530. Min Act: -0.0001
Data Index: 1534071 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1514. Min Act: -0.0001
Data Index: 1585370 (Python Code)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1889. Min Range: -0.1889
Max Act: 0.1561. Min Act: -0.0001
Data Index: 685380 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19