Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1091 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 4.6892. Min Range: -4.6892
Max Act: 3.8740. Min Act: -0.0000
Data Index: 933814 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.6784. Min Act: -0.0000
Data Index: 1258502 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.1226. Min Act: -0.0000
Data Index: 704389 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.2360. Min Act: -0.0000
Data Index: 441338 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.1875. Min Act: -0.0000
Data Index: 201233 (The Pile)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.6892. Min Act: -0.0000
Data Index: 221957 (The Pile)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6892. Min Range: -4.6892
Max Act: 3.9008. Min Act: -0.0000
Data Index: 1708715 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.3714. Min Act: -0.0000
Data Index: 1532588 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.1865. Min Act: -0.0000
Data Index: 25215 (The Pile)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.1608. Min Act: -0.0000
Data Index: 1962790 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6892. Min Range: -4.6892
Max Act: 3.8150. Min Act: -0.0000
Data Index: 855864 (The Pile)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.0173. Min Act: -0.0000
Data Index: 60254 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6892. Min Range: -4.6892
Max Act: 3.8298. Min Act: -0.0000
Data Index: 173927 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6892. Min Range: -4.6892
Max Act: 3.9495. Min Act: -0.0000
Data Index: 370207 (The Pile)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6892. Min Range: -4.6892
Max Act: 3.9668. Min Act: -0.0000
Data Index: 260398 (The Pile)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6892. Min Range: -4.6892
Max Act: 3.7769. Min Act: -0.0000
Data Index: 1474108 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6892. Min Range: -4.6892
Max Act: 4.0356. Min Act: -0.0000
Data Index: 863702 (The Pile)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6892. Min Range: -4.6892
Max Act: 3.8689. Min Act: -0.0000
Data Index: 117235 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6892. Min Range: -4.6892
Max Act: 3.6973. Min Act: -0.0000
Data Index: 1901586 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6892. Min Range: -4.6892
Max Act: 3.9321. Min Act: -0.0000
Data Index: 1905305 (The Pile)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19