Model: None
Dataset: The Pile
Neuron 223 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.6750. Min Act: -0.1700
Data Index: 5394839 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.5967. Min Act: -0.1700
Data Index: 3375685 (The Pile)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.5811. Min Act: -0.1700
Data Index: 583557 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.5654. Min Act: -0.1700
Data Index: 7200240 (The Pile)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.5028. Min Act: -0.1700
Data Index: 7314881 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4871. Min Act: -0.1700
Data Index: 8155258 (The Pile)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4871. Min Act: -0.1700
Data Index: 9986821 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4558. Min Act: -0.1700
Data Index: 5700388 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4401. Min Act: -0.1700
Data Index: 5372631 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4401. Min Act: -0.1700
Data Index: 3892799 (The Pile)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4401. Min Act: -0.1700
Data Index: 199421 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4401. Min Act: -0.1700
Data Index: 4526821 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4244. Min Act: -0.1700
Data Index: 7492796 (The Pile)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4244. Min Act: -0.1700
Data Index: 7352645 (The Pile)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4244. Min Act: -0.1700
Data Index: 5262308 (The Pile)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4087. Min Act: -0.1700
Data Index: 6338644 (The Pile)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4087. Min Act: -0.1700
Data Index: 9078818 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.3930. Min Act: -0.1700
Data Index: 9214702 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.3930. Min Act: -0.1700
Data Index: 203843 (The Pile)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.3930. Min Act: -0.1700
Data Index: 7054101 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19