Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2267 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.7916. Min Act: 0.0000
Data Index: 960575 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.7481. Min Act: -0.0000
Data Index: 1140154 (The Pile)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.7835. Min Act: -0.0000
Data Index: 1575528 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.6107. Min Act: 0.0000
Data Index: 839320 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.4738. Min Act: -0.0000
Data Index: 1353096 (The Pile)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.4389. Min Act: -0.0000
Data Index: 26213 (The Pile)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.3867. Min Act: 0.0000
Data Index: 1730208 (The Pile)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.2835. Min Act: 0.0000
Data Index: 1294606 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.2913. Min Act: -0.0000
Data Index: 1496855 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.4579. Min Act: -0.0000
Data Index: 1726305 (The Pile)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.3153. Min Act: -0.0000
Data Index: 635552 (The Pile)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.3254. Min Act: 0.0000
Data Index: 1204868 (The Pile)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.2061. Min Act: 0.0000
Data Index: 914167 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.1071. Min Act: -0.0000
Data Index: 851466 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.1474. Min Act: 0.0000
Data Index: 466256 (The Pile)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.2173. Min Act: -0.0000
Data Index: 1878913 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.1126. Min Act: -0.0000
Data Index: 1395703 (The Pile)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.0781. Min Act: -0.0000
Data Index: 1748583 (The Pile)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.0312. Min Act: 0.0001
Data Index: 798887 (The Pile)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7916. Min Range: -1.7916
Max Act: 1.0282. Min Act: -0.0000
Data Index: 1122842 (The Pile)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19