Model: None
Dataset: The Pile
Neuron 1673 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.9549. Min Act: -0.1700
Data Index: 7793458 (The Pile)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8598. Min Act: -0.1700
Data Index: 5966463 (The Pile)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8598. Min Act: -0.1700
Data Index: 4973613 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8598. Min Act: -0.1700
Data Index: 10418224 (The Pile)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8598. Min Act: -0.1700
Data Index: 7004934 (The Pile)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8439. Min Act: -0.1700
Data Index: 1407831 (The Pile)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8280. Min Act: -0.1700
Data Index: 2008319 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7961. Min Act: -0.1700
Data Index: 4032786 (The Pile)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7961. Min Act: -0.1700
Data Index: 6085492 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7961. Min Act: -0.1700
Data Index: 10734835 (The Pile)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 3100288 (The Pile)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 5700266 (The Pile)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 231688 (The Pile)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 8655084 (The Pile)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 9194365 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 9654842 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 1204760 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 9693787 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 483134 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 3286250 (The Pile)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19