Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3200 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.1747. Min Act: -0.0003
Data Index: 1653741 (The Pile)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.1456. Min Act: -0.0003
Data Index: 1673028 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.1017. Min Act: -0.0003
Data Index: 1402868 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.1019. Min Act: -0.0003
Data Index: 1590806 (The Pile)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0998. Min Act: -0.0003
Data Index: 248251 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0862. Min Act: -0.0003
Data Index: 1351215 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0874. Min Act: -0.0003
Data Index: 1067333 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0908. Min Act: -0.0003
Data Index: 1709584 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0810. Min Act: -0.0003
Data Index: 948358 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0885. Min Act: -0.0003
Data Index: 939339 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0777. Min Act: -0.0003
Data Index: 94265 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0752. Min Act: -0.0003
Data Index: 114127 (The Pile)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0734. Min Act: -0.0003
Data Index: 1400241 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0715. Min Act: -0.0003
Data Index: 375133 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0711. Min Act: -0.0003
Data Index: 433302 (The Pile)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0728. Min Act: -0.0003
Data Index: 199150 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0730. Min Act: -0.0003
Data Index: 452406 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0636. Min Act: -0.0003
Data Index: 1357443 (The Pile)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0697. Min Act: -0.0003
Data Index: 1191104 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1747. Min Range: -0.1747
Max Act: 0.0695. Min Act: -0.0003
Data Index: 876214 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19