Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1562 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 4.1996. Min Range: -4.1996
Max Act: 4.1996. Min Act: -0.0000
Data Index: 1179597 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1996. Min Range: -4.1996
Max Act: 4.0245. Min Act: -0.0000
Data Index: 1482809 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.6121. Min Act: -0.0000
Data Index: 698226 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.8852. Min Act: -0.0000
Data Index: 491809 (The Pile)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1996. Min Range: -4.1996
Max Act: 4.0509. Min Act: -0.0000
Data Index: 345030 (The Pile)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.8446. Min Act: -0.0000
Data Index: 20026 (The Pile)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.5689. Min Act: -0.0000
Data Index: 1119586 (The Pile)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.7137. Min Act: -0.0000
Data Index: 920515 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.8181. Min Act: -0.0000
Data Index: 248772 (The Pile)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.6682. Min Act: -0.0000
Data Index: 439206 (The Pile)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.5040. Min Act: -0.0000
Data Index: 988486 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.8051. Min Act: -0.0000
Data Index: 1938473 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.6316. Min Act: -0.0000
Data Index: 198310 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.4709. Min Act: -0.0000
Data Index: 348387 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.4788. Min Act: -0.0000
Data Index: 993481 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.4617. Min Act: -0.0000
Data Index: 180060 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.4485. Min Act: -0.0000
Data Index: 672954 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.5621. Min Act: -0.0000
Data Index: 956527 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.6657. Min Act: -0.0000
Data Index: 66980 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1996. Min Range: -4.1996
Max Act: 3.5156. Min Act: -0.0000
Data Index: 579760 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19