Model: None
Dataset: The Pile
Neuron 4021 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6812. Min Act: -0.1700
Data Index: 1020828 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6812. Min Act: -0.1700
Data Index: 5870560 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6656. Min Act: -0.1700
Data Index: 1887718 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6499. Min Act: -0.1700
Data Index: 97165 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6499. Min Act: -0.1700
Data Index: 7378388 (The Pile)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6499. Min Act: -0.1700
Data Index: 4725019 (The Pile)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6499. Min Act: -0.1700
Data Index: 1511398 (The Pile)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6343. Min Act: -0.1700
Data Index: 5217261 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6343. Min Act: -0.1700
Data Index: 917034 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6186. Min Act: -0.1700
Data Index: 9728583 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6186. Min Act: -0.1700
Data Index: 516042 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6186. Min Act: -0.1700
Data Index: 330101 (The Pile)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6186. Min Act: -0.1700
Data Index: 3676913 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6186. Min Act: -0.1700
Data Index: 3078570 (The Pile)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6186. Min Act: -0.1700
Data Index: 10541433 (The Pile)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6030. Min Act: -0.1700
Data Index: 4731510 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6030. Min Act: -0.1700
Data Index: 236278 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6030. Min Act: -0.1700
Data Index: 395583 (The Pile)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6030. Min Act: -0.1700
Data Index: 7436262 (The Pile)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6812. Min Range: -3.6812
Max Act: 3.6030. Min Act: -0.1700
Data Index: 2819075 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19