Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 64 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.5004. Min Act: -0.0001
Data Index: 1110917 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.2988. Min Act: -0.0000
Data Index: 416895 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.1324. Min Act: -0.0000
Data Index: 1698708 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.5340. Min Act: -0.0001
Data Index: 104564 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.6220. Min Act: -0.0001
Data Index: 659180 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.3153. Min Act: -0.0001
Data Index: 828331 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.5789. Min Act: -0.0000
Data Index: 940007 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.5367. Min Act: -0.0001
Data Index: 313599 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.6016. Min Act: -0.0000
Data Index: 1179775 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.2813. Min Act: -0.0001
Data Index: 70325 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.4285. Min Act: -0.0001
Data Index: 848339 (The Pile)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.2804. Min Act: -0.0001
Data Index: 394063 (The Pile)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.2821. Min Act: -0.0001
Data Index: 1378898 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.2668. Min Act: -0.0001
Data Index: 1381321 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.2504. Min Act: -0.0001
Data Index: 1242815 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.3804. Min Act: -0.0001
Data Index: 289954 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.3304. Min Act: -0.0001
Data Index: 1084665 (The Pile)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.1850. Min Act: -0.0001
Data Index: 1815761 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.0323. Min Act: -0.0001
Data Index: 495413 (The Pile)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5004. Min Range: -4.5004
Max Act: 2.7560. Min Act: -0.0001
Data Index: 1677035 (The Pile)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19