Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1949 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.2533. Min Range: -1.2533
Max Act: 1.2454. Min Act: -0.0000
Data Index: 1817796 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2533. Min Range: -1.2533
Max Act: 1.2533. Min Act: -0.0000
Data Index: 1790765 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2533. Min Range: -1.2533
Max Act: 1.1539. Min Act: -0.0000
Data Index: 620450 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2533. Min Range: -1.2533
Max Act: 1.0637. Min Act: -0.0000
Data Index: 1846804 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2533. Min Range: -1.2533
Max Act: 1.0356. Min Act: -0.0000
Data Index: 1338037 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2533. Min Range: -1.2533
Max Act: 1.0206. Min Act: -0.0000
Data Index: 1700796 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2533. Min Range: -1.2533
Max Act: 0.9382. Min Act: -0.0000
Data Index: 1138794 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2533. Min Range: -1.2533
Max Act: 1.0416. Min Act: -0.0000
Data Index: 855188 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2533. Min Range: -1.2533
Max Act: 0.9010. Min Act: -0.0000
Data Index: 247250 (The Pile)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2533. Min Range: -1.2533
Max Act: 1.0368. Min Act: -0.0000
Data Index: 330962 (The Pile)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2533. Min Range: -1.2533
Max Act: 0.9667. Min Act: -0.0000
Data Index: 361744 (The Pile)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2533. Min Range: -1.2533
Max Act: 0.8837. Min Act: -0.0000
Data Index: 1984444 (The Pile)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2533. Min Range: -1.2533
Max Act: 0.8849. Min Act: -0.0000
Data Index: 1203032 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2533. Min Range: -1.2533
Max Act: 0.8611. Min Act: -0.0000
Data Index: 636667 (The Pile)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2533. Min Range: -1.2533
Max Act: 0.9865. Min Act: -0.0000
Data Index: 1620407 (The Pile)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2533. Min Range: -1.2533
Max Act: 0.9676. Min Act: -0.0000
Data Index: 1746202 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2533. Min Range: -1.2533
Max Act: 0.9858. Min Act: -0.0000
Data Index: 54 (The Pile)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2533. Min Range: -1.2533
Max Act: 0.8038. Min Act: -0.0000
Data Index: 1701865 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2533. Min Range: -1.2533
Max Act: 0.9377. Min Act: -0.0000
Data Index: 470828 (The Pile)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2533. Min Range: -1.2533
Max Act: 0.8853. Min Act: -0.0000
Data Index: 719836 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19