Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1868 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3960. Min Act: -0.0001
Data Index: 340069 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3795. Min Act: -0.0001
Data Index: 1690901 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.4019. Min Act: -0.0001
Data Index: 1501353 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3690. Min Act: -0.0001
Data Index: 1226530 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3472. Min Act: -0.0001
Data Index: 1157658 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3665. Min Act: -0.0001
Data Index: 1201942 (The Pile)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3410. Min Act: -0.0001
Data Index: 1499310 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3339. Min Act: -0.0001
Data Index: 796658 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3448. Min Act: -0.0001
Data Index: 282319 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3567. Min Act: -0.0001
Data Index: 800510 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3211. Min Act: -0.0001
Data Index: 1777735 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3132. Min Act: -0.0001
Data Index: 660918 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3084. Min Act: -0.0001
Data Index: 523222 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3047. Min Act: -0.0001
Data Index: 547553 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3199. Min Act: -0.0001
Data Index: 395882 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3102. Min Act: -0.0001
Data Index: 43043 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.2923. Min Act: -0.0001
Data Index: 1268480 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3070. Min Act: -0.0001
Data Index: 702121 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.3022. Min Act: -0.0001
Data Index: 1636455 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4019. Min Range: -0.4019
Max Act: 0.2850. Min Act: -0.0001
Data Index: 1974284 (The Pile)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19