Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.4707. Min Act: -0.1700
Data Index: 3281082 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.4082. Min Act: -0.1700
Data Index: 2299457 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.4082. Min Act: -0.1700
Data Index: 8470148 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.4082. Min Act: -0.1700
Data Index: 39071 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.4082. Min Act: -0.1700
Data Index: 2943743 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.4082. Min Act: -0.1700
Data Index: 2943746 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3457. Min Act: -0.1700
Data Index: 608710 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3457. Min Act: -0.1700
Data Index: 477271 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3457. Min Act: -0.1700
Data Index: 1451165 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3457. Min Act: -0.1698
Data Index: 5394785 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3457. Min Act: -0.1700
Data Index: 2918306 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3457. Min Act: -0.1700
Data Index: 7206001 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3457. Min Act: -0.1700
Data Index: 2630721 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3457. Min Act: -0.1700
Data Index: 2560364 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3145. Min Act: -0.1700
Data Index: 110889 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3145. Min Act: -0.1700
Data Index: 3425423 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3457. Min Act: -0.1700
Data Index: 4822893 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3145. Min Act: -0.1700
Data Index: 375366 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3145. Min Act: -0.1700
Data Index: 4155663 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4707. Min Range: -5.4707
Max Act: 5.3145. Min Act: -0.1700
Data Index: 4975405 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19