Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 557 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 2.2512. Min Range: -2.2512
Max Act: 2.1633. Min Act: -0.0000
Data Index: 357991 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2512. Min Range: -2.2512
Max Act: 2.2512. Min Act: -0.0001
Data Index: 1407231 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2512. Min Range: -2.2512
Max Act: 2.1575. Min Act: -0.0001
Data Index: 1420761 (The Pile)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.0299. Min Act: -0.0001
Data Index: 197363 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2512. Min Range: -2.2512
Max Act: 1.0789. Min Act: -0.0001
Data Index: 1145311 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.5454. Min Act: -0.0001
Data Index: 1252284 (The Pile)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.4477. Min Act: -0.0000
Data Index: 1846636 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2512. Min Range: -2.2512
Max Act: 1.9764. Min Act: -0.0001
Data Index: 603665 (The Pile)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.6953. Min Act: -0.0001
Data Index: 677716 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2512. Min Range: -2.2512
Max Act: 1.2846. Min Act: -0.0001
Data Index: 358866 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.2547. Min Act: -0.0000
Data Index: 1947972 (The Pile)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.2808. Min Act: -0.0000
Data Index: 176553 (The Pile)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.0912. Min Act: -0.0000
Data Index: 1384491 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.5317. Min Act: -0.0000
Data Index: 1477968 (The Pile)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.3665. Min Act: -0.0000
Data Index: 1037463 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.3904. Min Act: -0.0001
Data Index: 1120818 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.2693. Min Act: -0.0001
Data Index: 1401996 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.3750. Min Act: -0.0001
Data Index: 727534 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.3670. Min Act: -0.0001
Data Index: 1727774 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2512. Min Range: -2.2512
Max Act: 0.2925. Min Act: -0.0001
Data Index: 97986 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19