Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 163 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.1615. Min Act: -0.0000
Data Index: 1397849 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.2305. Min Act: -0.0000
Data Index: 1302041 (The Pile)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.1390. Min Act: -0.0000
Data Index: 179183 (The Pile)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.1611. Min Act: -0.0000
Data Index: 278936 (The Pile)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.1096. Min Act: -0.0000
Data Index: 566487 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0820. Min Act: -0.0000
Data Index: 1779539 (The Pile)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0796. Min Act: -0.0000
Data Index: 1410362 (The Pile)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0643. Min Act: -0.0000
Data Index: 279267 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0527. Min Act: -0.0000
Data Index: 938646 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0870. Min Act: -0.0000
Data Index: 1495810 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.1015. Min Act: -0.0000
Data Index: 1891677 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0646. Min Act: -0.0000
Data Index: 1877016 (The Pile)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0408. Min Act: -0.0000
Data Index: 1479547 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0643. Min Act: -0.0000
Data Index: 894897 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0650. Min Act: -0.0000
Data Index: 803885 (The Pile)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0332. Min Act: -0.0000
Data Index: 930012 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0251. Min Act: -0.0000
Data Index: 536605 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0102. Min Act: -0.0000
Data Index: 580354 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0311. Min Act: -0.0000
Data Index: 482713 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2305. Min Range: -1.2305
Max Act: 1.0692. Min Act: -0.0000
Data Index: 1267449 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19