Model: SoLU Model: 2 Layers, 2944 Neurons per Layer
Dataset: The Pile
Neuron 2807 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l-pile')
Text #0
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0132. Min Act: -0.0001
Data Index: 1487959 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0132. Min Act: -0.0001
Data Index: 467289 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0132. Min Act: -0.0001
Data Index: 1697999 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0130. Min Act: -0.0001
Data Index: 1353904 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0131. Min Act: -0.0001
Data Index: 1274552 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0131. Min Act: -0.0001
Data Index: 1322664 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0128. Min Act: -0.0001
Data Index: 790092 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0127. Min Act: -0.0001
Data Index: 1812393 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0130. Min Act: -0.0001
Data Index: 762376 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0126. Min Act: -0.0002
Data Index: 321640 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0126. Min Act: -0.0002
Data Index: 1105316 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0126. Min Act: -0.0001
Data Index: 1150325 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0123. Min Act: -0.0002
Data Index: 1189211 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0124. Min Act: -0.0001
Data Index: 1010796 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0125. Min Act: -0.0001
Data Index: 1171173 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0122. Min Act: -0.0001
Data Index: 1223740 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0122. Min Act: -0.0001
Data Index: 292645 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0120. Min Act: -0.0001
Data Index: 1998138 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0121. Min Act: -0.0002
Data Index: 726742 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0132. Min Range: -0.0132
Max Act: 0.0119. Min Act: -0.0001
Data Index: 1148303 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19