Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2349 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.3898. Min Act: -0.0001
Data Index: 875964 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.3414. Min Act: -0.0001
Data Index: 677676 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.2690. Min Act: -0.0001
Data Index: 1890216 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.2863. Min Act: -0.0001
Data Index: 1619065 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.2823. Min Act: -0.0001
Data Index: 1060697 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.2358. Min Act: -0.0001
Data Index: 468699 (The Pile)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.3027. Min Act: -0.0001
Data Index: 1096682 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.3233. Min Act: -0.0001
Data Index: 680441 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.3288. Min Act: -0.0001
Data Index: 883087 (The Pile)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.3350. Min Act: -0.0001
Data Index: 998059 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.1914. Min Act: -0.0001
Data Index: 1263689 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.2675. Min Act: -0.0001
Data Index: 1475902 (The Pile)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.1975. Min Act: -0.0001
Data Index: 1953766 (The Pile)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.2314. Min Act: -0.0001
Data Index: 421068 (The Pile)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.2019. Min Act: -0.0001
Data Index: 421771 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.2608. Min Act: -0.0001
Data Index: 854758 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.1421. Min Act: -0.0001
Data Index: 103904 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.2200. Min Act: -0.0001
Data Index: 1606485 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.2062. Min Act: -0.0001
Data Index: 94053 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3898. Min Range: -1.3898
Max Act: 1.1728. Min Act: -0.0001
Data Index: 1810002 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19