Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1687 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.8187. Min Act: -0.1700
Data Index: 6530679 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.5687. Min Act: -0.1700
Data Index: 6045202 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.4750. Min Act: -0.1700
Data Index: 2962768 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.4750. Min Act: -0.1700
Data Index: 377762 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.4437. Min Act: -0.1700
Data Index: 3042845 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.4125. Min Act: -0.1700
Data Index: 173856 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.4125. Min Act: -0.1700
Data Index: 3324303 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.3812. Min Act: -0.1700
Data Index: 7238289 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.3812. Min Act: -0.1700
Data Index: 7637077 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.3812. Min Act: -0.1700
Data Index: 7122652 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.3812. Min Act: -0.1700
Data Index: 1151130 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.3812. Min Act: -0.1700
Data Index: 6375661 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.3500. Min Act: -0.1700
Data Index: 8221618 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.3500. Min Act: -0.1700
Data Index: 5475925 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.3500. Min Act: -0.1700
Data Index: 3294330 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.3500. Min Act: -0.1700
Data Index: 8340031 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.3187. Min Act: -0.1700
Data Index: 3176951 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.3187. Min Act: -0.1700
Data Index: 7792108 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.2875. Min Act: -0.1700
Data Index: 6576565 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8187. Min Range: -4.8187
Max Act: 4.3187. Min Act: -0.1700
Data Index: 4882391 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19