Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 694 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.8806. Min Act: -0.1700
Data Index: 3955818 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.8181. Min Act: -0.1700
Data Index: 6168435 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.7556. Min Act: -0.1700
Data Index: 7770872 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.6931. Min Act: -0.1700
Data Index: 6396295 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.6931. Min Act: -0.1700
Data Index: 4484818 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.6931. Min Act: -0.1700
Data Index: 1898346 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.6931. Min Act: -0.1700
Data Index: 3503968 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.5681. Min Act: -0.1700
Data Index: 7690189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.5681. Min Act: -0.1700
Data Index: 5216175 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.5056. Min Act: -0.1700
Data Index: 3717379 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.5368. Min Act: -0.1700
Data Index: 7050810 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.5368. Min Act: -0.1700
Data Index: 2185687 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.5056. Min Act: -0.1700
Data Index: 2611081 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.5056. Min Act: -0.1700
Data Index: 7067333 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.5056. Min Act: -0.1700
Data Index: 6440815 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.4431. Min Act: -0.1700
Data Index: 2924648 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.4743. Min Act: -0.1700
Data Index: 129999 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.4118. Min Act: -0.1700
Data Index: 3319235 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.4118. Min Act: -0.1700
Data Index: 1835580 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8806. Min Range: -6.8806
Max Act: 6.3806. Min Act: -0.1700
Data Index: 4205145 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19