Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 591 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.1145. Min Act: -0.0001
Data Index: 892190 (The Pile)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.1087. Min Act: -0.0001
Data Index: 1812664 (The Pile)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.1117. Min Act: -0.0001
Data Index: 1339032 (The Pile)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.1117. Min Act: -0.0001
Data Index: 1809321 (The Pile)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.1102. Min Act: -0.0001
Data Index: 818333 (The Pile)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.1108. Min Act: -0.0001
Data Index: 528238 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.1091. Min Act: -0.0001
Data Index: 1273119 (The Pile)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.1005. Min Act: -0.0001
Data Index: 358535 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.1023. Min Act: -0.0001
Data Index: 141387 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.0999. Min Act: -0.0001
Data Index: 1714995 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.1042. Min Act: -0.0001
Data Index: 1068592 (The Pile)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.0949. Min Act: -0.0001
Data Index: 820337 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.1032. Min Act: -0.0001
Data Index: 1327646 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.0933. Min Act: -0.0001
Data Index: 590191 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.0918. Min Act: -0.0001
Data Index: 28126 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.0920. Min Act: -0.0001
Data Index: 446746 (The Pile)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.0919. Min Act: -0.0001
Data Index: 673167 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.0895. Min Act: -0.0001
Data Index: 228132 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.0917. Min Act: -0.0001
Data Index: 1964668 (The Pile)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1145. Min Range: -0.1145
Max Act: 0.0935. Min Act: -0.0001
Data Index: 659349 (The Pile)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19