Model: SoLU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1916 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')
Text #0
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0152. Min Act: -0.0006
Data Index: 1105253 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0136. Min Act: -0.0006
Data Index: 748373 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0134. Min Act: -0.0006
Data Index: 1067208 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0130. Min Act: -0.0006
Data Index: 1249477 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0126. Min Act: -0.0006
Data Index: 139345 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0127. Min Act: -0.0007
Data Index: 340438 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0123. Min Act: -0.0006
Data Index: 5615 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0120. Min Act: -0.0006
Data Index: 1121096 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0120. Min Act: -0.0006
Data Index: 1028951 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0120. Min Act: -0.0006
Data Index: 1349100 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0118. Min Act: -0.0006
Data Index: 284771 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0118. Min Act: -0.0006
Data Index: 786694 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0115. Min Act: -0.0005
Data Index: 1453933 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0116. Min Act: -0.0006
Data Index: 1268903 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0115. Min Act: -0.0006
Data Index: 661719 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0117. Min Act: -0.0006
Data Index: 688764 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0113. Min Act: -0.0005
Data Index: 110943 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0111. Min Act: -0.0006
Data Index: 1122662 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0111. Min Act: -0.0006
Data Index: 306730 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0152. Min Range: -0.0152
Max Act: 0.0110. Min Act: -0.0005
Data Index: 1445252 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19