Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 689 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0164. Min Act: -0.0001
Data Index: 137324 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0157. Min Act: -0.0001
Data Index: 1353050 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0146. Min Act: -0.0001
Data Index: 164286 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0140. Min Act: -0.0001
Data Index: 131496 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0135. Min Act: -0.0001
Data Index: 1872785 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0135. Min Act: -0.0001
Data Index: 1230357 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0132. Min Act: -0.0001
Data Index: 223152 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0132. Min Act: -0.0001
Data Index: 1094105 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0129. Min Act: -0.0001
Data Index: 1541733 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0128. Min Act: -0.0001
Data Index: 1080692 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0127. Min Act: -0.0001
Data Index: 1706983 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0127. Min Act: -0.0001
Data Index: 387834 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0128. Min Act: -0.0001
Data Index: 964549 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0125. Min Act: -0.0001
Data Index: 862292 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0124. Min Act: -0.0001
Data Index: 999770 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0124. Min Act: -0.0001
Data Index: 125006 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0124. Min Act: -0.0001
Data Index: 1398178 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0123. Min Act: -0.0001
Data Index: 1766619 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0122. Min Act: -0.0001
Data Index: 481252 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0164. Min Range: -0.0164
Max Act: 0.0121. Min Act: -0.0000
Data Index: 360778 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19