Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 4603 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.4484. Min Act: -0.0002
Data Index: 965333 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.4484. Min Act: -0.0002
Data Index: 1890066 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.4484. Min Act: -0.0002
Data Index: 558092 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.4442. Min Act: -0.0002
Data Index: 295934 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3978. Min Act: -0.0002
Data Index: 1991579 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3946. Min Act: -0.0002
Data Index: 1231646 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3782. Min Act: -0.0002
Data Index: 1982410 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3761. Min Act: -0.0002
Data Index: 993602 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3704. Min Act: -0.0002
Data Index: 498633 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3603. Min Act: -0.0002
Data Index: 241843 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3524. Min Act: -0.0002
Data Index: 1758993 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3420. Min Act: -0.0002
Data Index: 715551 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3420. Min Act: -0.0002
Data Index: 1307261 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3420. Min Act: -0.0002
Data Index: 579647 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3350. Min Act: -0.0002
Data Index: 722388 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3339. Min Act: -0.0002
Data Index: 1941140 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3144. Min Act: -0.0002
Data Index: 682094 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3014. Min Act: -0.0002
Data Index: 647273 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3097. Min Act: -0.0002
Data Index: 679248 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4484. Min Range: -0.4484
Max Act: 0.3097. Min Act: -0.0002
Data Index: 606785 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19