Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 916 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 3.2017. Min Range: -3.2017
Max Act: 3.2017. Min Act: -0.0000
Data Index: 219764 (The Pile)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.8824. Min Act: -0.0000
Data Index: 1527965 (The Pile)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.8687. Min Act: -0.0000
Data Index: 1164015 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2017. Min Range: -3.2017
Max Act: 3.0124. Min Act: -0.0000
Data Index: 1956188 (The Pile)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.7368. Min Act: -0.0000
Data Index: 761283 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.7992. Min Act: -0.0000
Data Index: 412791 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2017. Min Range: -3.2017
Max Act: 3.0159. Min Act: -0.0000
Data Index: 920111 (The Pile)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.8289. Min Act: -0.0000
Data Index: 9664 (The Pile)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.5350. Min Act: -0.0000
Data Index: 882936 (The Pile)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.5311. Min Act: -0.0000
Data Index: 212364 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.4014. Min Act: -0.0000
Data Index: 1278923 (The Pile)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.7457. Min Act: -0.0000
Data Index: 1819848 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.4882. Min Act: -0.0000
Data Index: 1669294 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.5770. Min Act: -0.0000
Data Index: 1574782 (The Pile)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.6877. Min Act: -0.0000
Data Index: 1282599 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.5299. Min Act: -0.0000
Data Index: 1910272 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.6518. Min Act: -0.0000
Data Index: 1125584 (The Pile)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.4740. Min Act: -0.0000
Data Index: 105982 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.4882. Min Act: -0.0000
Data Index: 1246617 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2017. Min Range: -3.2017
Max Act: 2.3674. Min Act: -0.0000
Data Index: 938244 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19