Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3002 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.6649. Min Act: -0.1700
Data Index: 2925893 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.6023. Min Act: -0.1700
Data Index: 6708741 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.6023. Min Act: -0.1700
Data Index: 1799106 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.6023. Min Act: -0.1700
Data Index: 4549084 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5867. Min Act: -0.1700
Data Index: 7746914 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5710. Min Act: -0.1700
Data Index: 6080009 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5554. Min Act: -0.1700
Data Index: 3958923 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5397. Min Act: -0.1700
Data Index: 1845869 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5397. Min Act: -0.1700
Data Index: 4291227 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5240. Min Act: -0.1700
Data Index: 6424133 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5240. Min Act: -0.1700
Data Index: 6379410 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5240. Min Act: -0.1700
Data Index: 2319767 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5240. Min Act: -0.1700
Data Index: 7939869 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5084. Min Act: -0.1700
Data Index: 8031125 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5240. Min Act: -0.1700
Data Index: 7891622 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5084. Min Act: -0.1700
Data Index: 6535962 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5084. Min Act: -0.1700
Data Index: 4416013 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5084. Min Act: -0.1700
Data Index: 6822476 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5084. Min Act: -0.1700
Data Index: 5869934 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6649. Min Range: -3.6649
Max Act: 3.5084. Min Act: -0.1700
Data Index: 938307 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19