Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6263 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2170. Min Range: -7.2170
Max Act: 7.2170. Min Act: -0.1700
Data Index: 8184827 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.6857. Min Act: -0.1700
Data Index: 7530291 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.5920. Min Act: -0.1700
Data Index: 2361654 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.5295. Min Act: -0.1700
Data Index: 879995 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.4982. Min Act: -0.1700
Data Index: 1578695 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.4982. Min Act: -0.1700
Data Index: 4467082 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.4670. Min Act: -0.1700
Data Index: 1968926 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.4357. Min Act: -0.1700
Data Index: 7274949 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.4045. Min Act: -0.1700
Data Index: 3877887 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.4045. Min Act: -0.1700
Data Index: 6151869 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.4357. Min Act: -0.1700
Data Index: 4334905 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.4045. Min Act: -0.1700
Data Index: 3385309 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.4045. Min Act: -0.1700
Data Index: 1526861 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.3732. Min Act: -0.1700
Data Index: 8361949 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.4045. Min Act: -0.1700
Data Index: 4013826 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.3732. Min Act: -0.1700
Data Index: 2981283 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.3732. Min Act: -0.1700
Data Index: 8361950 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.4045. Min Act: -0.1700
Data Index: 7461694 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.3107. Min Act: -0.1700
Data Index: 2721796 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2170. Min Range: -7.2170
Max Act: 6.3107. Min Act: -0.1700
Data Index: 2461401 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19