Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.6305. Min Act: -0.1700
Data Index: 2368777 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.4117. Min Act: -0.1700
Data Index: 7457416 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.3805. Min Act: -0.1700
Data Index: 422736 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.3492. Min Act: -0.1700
Data Index: 4549006 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.3180. Min Act: -0.1700
Data Index: 7477179 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.3180. Min Act: -0.1700
Data Index: 7945220 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.2242. Min Act: -0.1700
Data Index: 8267989 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.1617. Min Act: -0.1700
Data Index: 3867955 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.2242. Min Act: -0.1700
Data Index: 8142759 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.1617. Min Act: -0.1700
Data Index: 2021403 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.1305. Min Act: -0.1700
Data Index: 4548792 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.1617. Min Act: -0.1700
Data Index: 1470458 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.1305. Min Act: -0.1700
Data Index: 8585076 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.1305. Min Act: -0.1700
Data Index: 3242754 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.1305. Min Act: -0.1700
Data Index: 5281839 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.1305. Min Act: -0.1700
Data Index: 6936302 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.1305. Min Act: -0.1700
Data Index: 2351382 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.0680. Min Act: -0.1700
Data Index: 1275856 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.0992. Min Act: -0.1700
Data Index: 3626090 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6305. Min Range: -6.6305
Max Act: 6.0992. Min Act: -0.1700
Data Index: 6856003 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19