Model: None
Dataset: The Pile
Neuron 1120 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0970. Min Act: -0.1700
Data Index: 4293963 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0654. Min Act: -0.1700
Data Index: 7561402 (The Pile)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0654. Min Act: -0.1700
Data Index: 886217 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0496. Min Act: -0.1700
Data Index: 2413499 (The Pile)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0496. Min Act: -0.1700
Data Index: 1662256 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0496. Min Act: -0.1700
Data Index: 5525722 (The Pile)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0338. Min Act: -0.1700
Data Index: 458818 (The Pile)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0338. Min Act: -0.1700
Data Index: 8339552 (The Pile)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0180. Min Act: -0.1700
Data Index: 5387024 (The Pile)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0180. Min Act: -0.1700
Data Index: 579465 (The Pile)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0180. Min Act: -0.1700
Data Index: 2162360 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0180. Min Act: -0.1700
Data Index: 9645825 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0180. Min Act: -0.1700
Data Index: 1706311 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0022. Min Act: -0.1700
Data Index: 9859223 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0022. Min Act: -0.1700
Data Index: 9919853 (The Pile)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0022. Min Act: -0.1700
Data Index: 1960864 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0022. Min Act: -0.1700
Data Index: 10535949 (The Pile)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0022. Min Act: -0.1700
Data Index: 259519 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0970. Min Range: -3.0970
Max Act: 3.0022. Min Act: -0.1700
Data Index: 7654516 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0970. Min Range: -3.0970
Max Act: 2.9864. Min Act: -0.1700
Data Index: 2919099 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19