Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4650 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.4620. Min Act: -0.1700
Data Index: 8725476 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.4620. Min Act: -0.1700
Data Index: 2596017 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.2745. Min Act: -0.1700
Data Index: 1437313 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.2433. Min Act: -0.1700
Data Index: 7526024 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.2120. Min Act: -0.1700
Data Index: 6835917 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.1183. Min Act: -0.1700
Data Index: 5534271 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.1495. Min Act: -0.1700
Data Index: 686888 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0870. Min Act: -0.1700
Data Index: 4074157 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0870. Min Act: -0.1700
Data Index: 7384191 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0870. Min Act: -0.1700
Data Index: 2297449 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0558. Min Act: -0.1700
Data Index: 5034141 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0870. Min Act: -0.1700
Data Index: 454377 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0870. Min Act: -0.1700
Data Index: 5775018 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0558. Min Act: -0.1700
Data Index: 253580 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0558. Min Act: -0.1700
Data Index: 5534270 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0870. Min Act: -0.1700
Data Index: 7222923 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0245. Min Act: -0.1700
Data Index: 5706676 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0245. Min Act: -0.1700
Data Index: 5341254 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0245. Min Act: -0.1700
Data Index: 238493 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4620. Min Range: -6.4620
Max Act: 6.0245. Min Act: -0.1700
Data Index: 3649314 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19