Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3979 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0108. Min Act: -0.0001
Data Index: 758627 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0108. Min Act: -0.0001
Data Index: 1127726 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0101. Min Act: -0.0001
Data Index: 587222 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0095. Min Act: -0.0001
Data Index: 1827219 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0094. Min Act: -0.0001
Data Index: 23475 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0087. Min Act: -0.0001
Data Index: 210347 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0087. Min Act: -0.0001
Data Index: 1782627 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0088. Min Act: -0.0001
Data Index: 321029 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0084. Min Act: -0.0001
Data Index: 1226853 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0084. Min Act: -0.0001
Data Index: 617264 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0085. Min Act: -0.0001
Data Index: 1926930 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0082. Min Act: -0.0001
Data Index: 327236 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0082. Min Act: -0.0001
Data Index: 1438678 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0082. Min Act: -0.0001
Data Index: 1223262 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0082. Min Act: -0.0001
Data Index: 1329802 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0082. Min Act: -0.0001
Data Index: 530220 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0081. Min Act: -0.0001
Data Index: 1658769 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0081. Min Act: -0.0001
Data Index: 1337827 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0083. Min Act: -0.0001
Data Index: 222017 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0108. Min Range: -0.0108
Max Act: 0.0079. Min Act: -0.0001
Data Index: 1762903 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19