Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1991 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0274. Min Act: -0.0001
Data Index: 1567571 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0274. Min Act: -0.0001
Data Index: 788051 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0267. Min Act: -0.0001
Data Index: 1729515 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0267. Min Act: -0.0001
Data Index: 639995 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0267. Min Act: -0.0001
Data Index: 1322955 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0267. Min Act: -0.0001
Data Index: 1240867 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0267. Min Act: -0.0001
Data Index: 1780703 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0265. Min Act: -0.0001
Data Index: 1987278 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0265. Min Act: -0.0001
Data Index: 1745048 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0265. Min Act: -0.0001
Data Index: 769132 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0251. Min Act: -0.0001
Data Index: 1107219 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0251. Min Act: -0.0001
Data Index: 761845 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0251. Min Act: -0.0001
Data Index: 661264 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0251. Min Act: -0.0001
Data Index: 476861 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0251. Min Act: -0.0001
Data Index: 1306129 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0251. Min Act: -0.0001
Data Index: 174808 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0251. Min Act: -0.0001
Data Index: 1346749 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0251. Min Act: -0.0001
Data Index: 606319 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0251. Min Act: -0.0001
Data Index: 1356417 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0274. Min Range: -0.0274
Max Act: 0.0251. Min Act: -0.0001
Data Index: 1420247 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19