Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 141 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0279. Min Act: -0.0000
Data Index: 612161 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0276. Min Act: -0.0000
Data Index: 3885 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0275. Min Act: -0.0000
Data Index: 1498857 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0274. Min Act: -0.0000
Data Index: 1762812 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0271. Min Act: -0.0000
Data Index: 184093 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0271. Min Act: -0.0001
Data Index: 906794 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0271. Min Act: -0.0000
Data Index: 232639 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0271. Min Act: -0.0000
Data Index: 1356580 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0271. Min Act: -0.0000
Data Index: 1404279 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0271. Min Act: -0.0000
Data Index: 160263 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0271. Min Act: -0.0000
Data Index: 1874604 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0271. Min Act: -0.0000
Data Index: 1393429 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0269. Min Act: 0.0000
Data Index: 1205440 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0269. Min Act: -0.0000
Data Index: 1049076 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0268. Min Act: -0.0000
Data Index: 908758 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0267. Min Act: -0.0000
Data Index: 14063 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0268. Min Act: -0.0000
Data Index: 191846 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0265. Min Act: -0.0000
Data Index: 955604 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0256. Min Act: -0.0000
Data Index: 841444 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0279. Min Range: -0.0279
Max Act: 0.0265. Min Act: -0.0000
Data Index: 1119120 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19