Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3860 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0195. Min Act: -0.0001
Data Index: 1292569 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0195. Min Act: -0.0000
Data Index: 574096 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0194. Min Act: -0.0001
Data Index: 322617 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0194. Min Act: -0.0001
Data Index: 1645017 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0194. Min Act: -0.0000
Data Index: 1871854 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0192. Min Act: -0.0000
Data Index: 1997375 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0192. Min Act: -0.0001
Data Index: 15483 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0192. Min Act: -0.0000
Data Index: 1580182 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0192. Min Act: -0.0000
Data Index: 713000 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0192. Min Act: -0.0000
Data Index: 1914780 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0190. Min Act: -0.0000
Data Index: 1966238 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0188. Min Act: -0.0001
Data Index: 1559925 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0188. Min Act: -0.0000
Data Index: 768591 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0188. Min Act: -0.0000
Data Index: 1829171 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0188. Min Act: -0.0000
Data Index: 566499 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0188. Min Act: -0.0001
Data Index: 724156 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0187. Min Act: -0.0000
Data Index: 1490433 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0186. Min Act: -0.0000
Data Index: 750289 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0185. Min Act: -0.0001
Data Index: 1692385 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0195. Min Range: -0.0195
Max Act: 0.0184. Min Act: -0.0000
Data Index: 213931 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19