Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 613 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.9785. Min Act: -0.0000
Data Index: 1333257 (The Pile)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.6861. Min Act: -0.0000
Data Index: 1445946 (The Pile)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.7021. Min Act: -0.0000
Data Index: 1206478 (The Pile)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.6324. Min Act: -0.0000
Data Index: 732622 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5831. Min Act: -0.0000
Data Index: 1443635 (The Pile)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5888. Min Act: -0.0000
Data Index: 1940880 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5860. Min Act: -0.0000
Data Index: 1627910 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5991. Min Act: -0.0000
Data Index: 938029 (The Pile)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.6014. Min Act: -0.0000
Data Index: 1111109 (The Pile)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5619. Min Act: -0.0000
Data Index: 50607 (The Pile)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5985. Min Act: -0.0000
Data Index: 947212 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5965. Min Act: -0.0000
Data Index: 1632031 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5565. Min Act: -0.0000
Data Index: 469732 (The Pile)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5629. Min Act: -0.0000
Data Index: 937088 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5278. Min Act: -0.0000
Data Index: 743029 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5608. Min Act: -0.0000
Data Index: 78546 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5034. Min Act: -0.0000
Data Index: 60004 (The Pile)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5318. Min Act: -0.0000
Data Index: 758872 (The Pile)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5006. Min Act: -0.0000
Data Index: 1750002 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9785. Min Range: -0.9785
Max Act: 0.5279. Min Act: -0.0000
Data Index: 900626 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19