Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 386 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.7720. Min Act: -0.1700
Data Index: 5695582 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.7095. Min Act: -0.1700
Data Index: 7409371 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.6470. Min Act: -0.1700
Data Index: 1046928 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.6783. Min Act: -0.1700
Data Index: 7006915 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.5845. Min Act: -0.1700
Data Index: 6519448 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.5845. Min Act: -0.1700
Data Index: 2925716 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.5533. Min Act: -0.1700
Data Index: 3779487 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.5845. Min Act: -0.1700
Data Index: 3129228 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.5533. Min Act: -0.1700
Data Index: 918241 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.5845. Min Act: -0.1700
Data Index: 5506329 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.5533. Min Act: -0.1700
Data Index: 47433 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.5220. Min Act: -0.1700
Data Index: 813582 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.5533. Min Act: -0.1700
Data Index: 198226 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.4908. Min Act: -0.1700
Data Index: 3277740 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.4908. Min Act: -0.1700
Data Index: 6813875 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.5220. Min Act: -0.1700
Data Index: 7135239 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.4908. Min Act: -0.1700
Data Index: 2162165 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.4595. Min Act: -0.1700
Data Index: 5376044 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.4595. Min Act: -0.1700
Data Index: 4252787 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7720. Min Range: -5.7720
Max Act: 5.4283. Min Act: -0.1700
Data Index: 1330408 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19