Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.8673. Min Act: -0.1700
Data Index: 7478899 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.2735. Min Act: -0.1700
Data Index: 662714 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.2423. Min Act: -0.1700
Data Index: 83974 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.2110. Min Act: -0.1700
Data Index: 7509104 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.2110. Min Act: -0.1700
Data Index: 118469 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1798. Min Act: -0.1700
Data Index: 8611871 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1798. Min Act: -0.1700
Data Index: 5774069 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1798. Min Act: -0.1700
Data Index: 2408506 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1798. Min Act: -0.1700
Data Index: 8001377 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1798. Min Act: -0.1700
Data Index: 7698799 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1798. Min Act: -0.1700
Data Index: 2600650 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1485. Min Act: -0.1700
Data Index: 3253815 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1485. Min Act: -0.1700
Data Index: 3466473 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1485. Min Act: -0.1700
Data Index: 5915172 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1485. Min Act: -0.1700
Data Index: 688074 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1485. Min Act: -0.1700
Data Index: 8611875 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1485. Min Act: -0.1700
Data Index: 2548320 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1172. Min Act: -0.1700
Data Index: 4303789 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1172. Min Act: -0.1700
Data Index: 4411774 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.1172. Min Act: -0.1700
Data Index: 2169092 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19