Model: None
Dataset: The Pile
Neuron 847 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.4027. Min Act: -0.1700
Data Index: 1388221 (The Pile)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3870. Min Act: -0.1700
Data Index: 832802 (The Pile)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3713. Min Act: -0.1700
Data Index: 2383830 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3556. Min Act: -0.1700
Data Index: 256628 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3713. Min Act: -0.1700
Data Index: 6144186 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3399. Min Act: -0.1700
Data Index: 2933124 (The Pile)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3399. Min Act: -0.1700
Data Index: 1544121 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3399. Min Act: -0.1700
Data Index: 110654 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3242. Min Act: -0.1700
Data Index: 4518112 (The Pile)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3399. Min Act: -0.1700
Data Index: 666426 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3242. Min Act: -0.1700
Data Index: 7315811 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3242. Min Act: -0.1700
Data Index: 3324363 (The Pile)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3085. Min Act: -0.1700
Data Index: 9379611 (The Pile)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3085. Min Act: -0.1700
Data Index: 8228209 (The Pile)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3085. Min Act: -0.1700
Data Index: 313766 (The Pile)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3242. Min Act: -0.1700
Data Index: 7206349 (The Pile)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3085. Min Act: -0.1700
Data Index: 1377792 (The Pile)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3085. Min Act: -0.1700
Data Index: 3672108 (The Pile)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.3085. Min Act: -0.1700
Data Index: 1844261 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4027. Min Range: -3.4027
Max Act: 3.2928. Min Act: -0.1700
Data Index: 6150933 (The Pile)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19