Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5342 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.9923. Min Act: -0.1700
Data Index: 8427191 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 4973206 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 2241438 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8986. Min Act: -0.1700
Data Index: 2933588 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8986. Min Act: -0.1700
Data Index: 3715308 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8986. Min Act: -0.1700
Data Index: 4875644 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8986. Min Act: -0.1700
Data Index: 1244998 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 3016006 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 3450730 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 4891878 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 2506571 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8361. Min Act: -0.1700
Data Index: 4857511 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8361. Min Act: -0.1700
Data Index: 2357829 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8361. Min Act: -0.1700
Data Index: 6778976 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8361. Min Act: -0.1700
Data Index: 6030006 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8361. Min Act: -0.1700
Data Index: 5412437 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8361. Min Act: -0.1700
Data Index: 5725463 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8048. Min Act: -0.1700
Data Index: 1758615 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8361. Min Act: -0.1700
Data Index: 7665597 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8048. Min Act: -0.1700
Data Index: 3407507 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19