Model: None
Dataset: The Pile
Neuron 693 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.3915. Min Act: -0.1700
Data Index: 3076733 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.3602. Min Act: -0.1700
Data Index: 5331936 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.3290. Min Act: -0.1700
Data Index: 9831768 (The Pile)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.3290. Min Act: -0.1700
Data Index: 8353109 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.2977. Min Act: -0.1700
Data Index: 4733209 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.2665. Min Act: -0.1700
Data Index: 10351025 (The Pile)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.2352. Min Act: -0.1700
Data Index: 5211600 (The Pile)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.2352. Min Act: -0.1700
Data Index: 1818868 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.2039. Min Act: -0.1700
Data Index: 8898502 (The Pile)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.2039. Min Act: -0.1700
Data Index: 9588240 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.2039. Min Act: -0.1700
Data Index: 8282461 (The Pile)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.1727. Min Act: -0.1700
Data Index: 8039781 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.1727. Min Act: -0.1700
Data Index: 10194262 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.1727. Min Act: -0.1700
Data Index: 10178680 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.1727. Min Act: -0.1700
Data Index: 4191797 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.1727. Min Act: -0.1700
Data Index: 6899132 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.1727. Min Act: -0.1700
Data Index: 2830257 (The Pile)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.1414. Min Act: -0.1700
Data Index: 10110718 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.1414. Min Act: -0.1700
Data Index: 1859200 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3915. Min Range: -4.3915
Max Act: 4.1414. Min Act: -0.1700
Data Index: 4705176 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19