Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4406 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.8948. Min Act: -0.1700
Data Index: 7853588 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.8636. Min Act: -0.1700
Data Index: 6195224 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.7386. Min Act: -0.1700
Data Index: 1819313 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.7386. Min Act: -0.1700
Data Index: 784150 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.6761. Min Act: -0.1700
Data Index: 1193888 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.7073. Min Act: -0.1700
Data Index: 4773048 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.6761. Min Act: -0.1700
Data Index: 6619156 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.6136. Min Act: -0.1700
Data Index: 8166408 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.6136. Min Act: -0.1700
Data Index: 6567452 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.5823. Min Act: -0.1700
Data Index: 4453941 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.5198. Min Act: -0.1700
Data Index: 5081244 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.5198. Min Act: -0.1700
Data Index: 441270 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.5198. Min Act: -0.1700
Data Index: 4647586 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.5198. Min Act: -0.1700
Data Index: 3184093 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.5198. Min Act: -0.1700
Data Index: 6117519 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.4573. Min Act: -0.1700
Data Index: 6982771 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.4573. Min Act: -0.1700
Data Index: 2169172 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.4261. Min Act: -0.1700
Data Index: 7718458 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.4573. Min Act: -0.1700
Data Index: 6803422 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8948. Min Range: -6.8948
Max Act: 6.3948. Min Act: -0.1700
Data Index: 7016433 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19