Model: None
Dataset: The Pile
Neuron 2955 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.6119. Min Act: -0.1700
Data Index: 10614936 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.5962. Min Act: -0.1700
Data Index: 2469173 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.5806. Min Act: -0.1700
Data Index: 5547525 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.5493. Min Act: -0.1700
Data Index: 8596396 (The Pile)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.5336. Min Act: -0.1700
Data Index: 10669599 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.5336. Min Act: -0.1700
Data Index: 8438014 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.5179. Min Act: -0.1700
Data Index: 4072028 (The Pile)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.5023. Min Act: -0.1700
Data Index: 9623173 (The Pile)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.5023. Min Act: -0.1700
Data Index: 2408878 (The Pile)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.5023. Min Act: -0.1700
Data Index: 1990677 (The Pile)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.4866. Min Act: -0.1700
Data Index: 10645627 (The Pile)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.4866. Min Act: -0.1700
Data Index: 7966135 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.4866. Min Act: -0.1700
Data Index: 3683354 (The Pile)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.4709. Min Act: -0.1700
Data Index: 8801807 (The Pile)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.4709. Min Act: -0.1700
Data Index: 2176090 (The Pile)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.4709. Min Act: -0.1700
Data Index: 1162216 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.4709. Min Act: -0.1700
Data Index: 2558804 (The Pile)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.4709. Min Act: -0.1700
Data Index: 9734932 (The Pile)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.4709. Min Act: -0.1700
Data Index: 9505871 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6119. Min Range: -3.6119
Max Act: 3.4552. Min Act: -0.1700
Data Index: 5745370 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19