Model: None
Dataset: The Pile
Neuron 1258 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.4690. Min Act: -0.1700
Data Index: 210760 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.4690. Min Act: -0.1700
Data Index: 6603790 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.4690. Min Act: -0.1700
Data Index: 4151324 (The Pile)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.4533. Min Act: -0.1700
Data Index: 5203689 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.4533. Min Act: -0.1700
Data Index: 2676156 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.4220. Min Act: -0.1700
Data Index: 4013685 (The Pile)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.4220. Min Act: -0.1700
Data Index: 7891715 (The Pile)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.4220. Min Act: -0.1700
Data Index: 4349809 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.4063. Min Act: -0.1700
Data Index: 129244 (The Pile)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.4063. Min Act: -0.1700
Data Index: 9487086 (The Pile)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.3906. Min Act: -0.1700
Data Index: 1887226 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.3906. Min Act: -0.1700
Data Index: 3407619 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.3906. Min Act: -0.1700
Data Index: 3730810 (The Pile)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.3749. Min Act: -0.1700
Data Index: 4019694 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.3592. Min Act: -0.1700
Data Index: 1688409 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.3592. Min Act: -0.1700
Data Index: 5599749 (The Pile)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.3592. Min Act: -0.1700
Data Index: 495831 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.3592. Min Act: -0.1700
Data Index: 6510760 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.3435. Min Act: -0.1700
Data Index: 7323489 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4690. Min Range: -3.4690
Max Act: 3.3278. Min Act: -0.1700
Data Index: 9104148 (The Pile)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19