Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3187 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.5130. Min Act: -0.1700
Data Index: 8346307 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.5130. Min Act: -0.1700
Data Index: 4204763 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.5130. Min Act: -0.1700
Data Index: 3718720 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.4974. Min Act: -0.1700
Data Index: 1597005 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.4661. Min Act: -0.1700
Data Index: 1443870 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.4504. Min Act: -0.1700
Data Index: 494375 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.4190. Min Act: -0.1700
Data Index: 2461081 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.4190. Min Act: -0.1700
Data Index: 4996976 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.4190. Min Act: -0.1700
Data Index: 3134708 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.4034. Min Act: -0.1700
Data Index: 1443830 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.4034. Min Act: -0.1700
Data Index: 2549874 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.4034. Min Act: -0.1700
Data Index: 7001567 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.3877. Min Act: -0.1700
Data Index: 632882 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.3720. Min Act: -0.1700
Data Index: 3086155 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.4034. Min Act: -0.1700
Data Index: 6279885 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.3877. Min Act: -0.1700
Data Index: 6748071 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.3877. Min Act: -0.1700
Data Index: 6103163 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.3720. Min Act: -0.1700
Data Index: 1554966 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.3720. Min Act: -0.1700
Data Index: 612076 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5130. Min Range: -3.5130
Max Act: 3.3720. Min Act: -0.1700
Data Index: 2556175 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19