Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2742 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.8622. Min Act: -0.0000
Data Index: 1179036 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.6025. Min Act: -0.0000
Data Index: 735628 (The Pile)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.6341. Min Act: -0.0000
Data Index: 1176223 (The Pile)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.3653. Min Act: -0.0000
Data Index: 1044510 (The Pile)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.3977. Min Act: -0.0000
Data Index: 814228 (The Pile)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.4684. Min Act: -0.0000
Data Index: 411928 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.3831. Min Act: -0.0000
Data Index: 888092 (The Pile)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.3764. Min Act: -0.0000
Data Index: 67845 (The Pile)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.2288. Min Act: -0.0000
Data Index: 285483 (The Pile)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.3894. Min Act: -0.0000
Data Index: 597889 (The Pile)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.4697. Min Act: -0.0000
Data Index: 780410 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.3120. Min Act: -0.0000
Data Index: 8440 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.3009. Min Act: -0.0000
Data Index: 475009 (The Pile)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.1834. Min Act: -0.0000
Data Index: 1720955 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.1992. Min Act: -0.0000
Data Index: 1934590 (The Pile)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.1572. Min Act: -0.0000
Data Index: 746467 (The Pile)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.1417. Min Act: -0.0000
Data Index: 257629 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.1941. Min Act: -0.0000
Data Index: 1014428 (The Pile)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.1925. Min Act: -0.0000
Data Index: 794985 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8622. Min Range: -1.8622
Max Act: 1.0469. Min Act: -0.0000
Data Index: 1143172 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19