Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4088 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1040. Min Range: -9.1040
Max Act: 9.1040. Min Act: -0.1700
Data Index: 160765 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.7290. Min Act: -0.1700
Data Index: 2823818 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.6665. Min Act: -0.1700
Data Index: 6159801 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.6040. Min Act: -0.1700
Data Index: 2372847 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.6040. Min Act: -0.1700
Data Index: 5313905 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.4790. Min Act: -0.1700
Data Index: 2299816 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.2915. Min Act: -0.1700
Data Index: 5495505 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.2915. Min Act: -0.1700
Data Index: 445706 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.2290. Min Act: -0.1700
Data Index: 6482980 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.2290. Min Act: -0.1700
Data Index: 6636385 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.1665. Min Act: -0.1700
Data Index: 8100967 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.1665. Min Act: -0.1700
Data Index: 4087065 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.1665. Min Act: -0.1700
Data Index: 4127217 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.1040. Min Act: -0.1700
Data Index: 4845687 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.1040. Min Act: -0.1700
Data Index: 970999 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.1040. Min Act: -0.1700
Data Index: 1648133 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.1040. Min Act: -0.1700
Data Index: 6081378 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.1040. Min Act: -0.1700
Data Index: 1861526 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.1040. Min Act: -0.1700
Data Index: 1906476 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1040. Min Range: -9.1040
Max Act: 8.0415. Min Act: -0.1700
Data Index: 3526891 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19