Model: None
Dataset: The Pile
Neuron 1087 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7639. Min Act: -0.1700
Data Index: 7965747 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7483. Min Act: -0.1700
Data Index: 843753 (The Pile)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7483. Min Act: -0.1700
Data Index: 2741834 (The Pile)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7483. Min Act: -0.1700
Data Index: 373658 (The Pile)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7483. Min Act: -0.1700
Data Index: 9324869 (The Pile)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7483. Min Act: -0.1700
Data Index: 2800859 (The Pile)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7483. Min Act: -0.1700
Data Index: 1969733 (The Pile)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 2812365 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 9342462 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 7876820 (The Pile)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 4453139 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 7317162 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 10066879 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 2936970 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 4991208 (The Pile)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 157868 (The Pile)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 96044 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 5214681 (The Pile)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 8530673 (The Pile)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7639. Min Range: -3.7639
Max Act: 3.7326. Min Act: -0.1700
Data Index: 5930541 (The Pile)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19