Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2485 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5699. Min Range: -8.5699
Max Act: 8.5699. Min Act: -0.1700
Data Index: 8096729 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5699. Min Range: -8.5699
Max Act: 8.5699. Min Act: -0.1700
Data Index: 7921313 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5699. Min Range: -8.5699
Max Act: 8.5074. Min Act: -0.1700
Data Index: 5965998 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5699. Min Range: -8.5699
Max Act: 8.5074. Min Act: -0.1700
Data Index: 2717232 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5699. Min Range: -8.5699
Max Act: 8.3824. Min Act: -0.1700
Data Index: 43364 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5699. Min Range: -8.5699
Max Act: 8.0699. Min Act: -0.1700
Data Index: 1172850 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5699. Min Range: -8.5699
Max Act: 8.0699. Min Act: -0.1700
Data Index: 223552 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5699. Min Range: -8.5699
Max Act: 8.0074. Min Act: -0.1700
Data Index: 5318321 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5699. Min Range: -8.5699
Max Act: 8.0074. Min Act: -0.1700
Data Index: 2123562 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5699. Min Range: -8.5699
Max Act: 8.0074. Min Act: -0.1700
Data Index: 1462856 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5699. Min Range: -8.5699
Max Act: 7.9449. Min Act: -0.1700
Data Index: 4872245 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5699. Min Range: -8.5699
Max Act: 7.9449. Min Act: -0.1700
Data Index: 1511441 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5699. Min Range: -8.5699
Max Act: 7.8824. Min Act: -0.1700
Data Index: 1420956 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5699. Min Range: -8.5699
Max Act: 7.8824. Min Act: -0.1700
Data Index: 2601777 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5699. Min Range: -8.5699
Max Act: 7.8824. Min Act: -0.1700
Data Index: 3559942 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5699. Min Range: -8.5699
Max Act: 7.8199. Min Act: -0.1700
Data Index: 7407693 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5699. Min Range: -8.5699
Max Act: 7.8199. Min Act: -0.1700
Data Index: 5749816 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5699. Min Range: -8.5699
Max Act: 7.8199. Min Act: -0.1700
Data Index: 6843259 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5699. Min Range: -8.5699
Max Act: 7.8199. Min Act: -0.1700
Data Index: 3082664 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5699. Min Range: -8.5699
Max Act: 7.8199. Min Act: -0.1700
Data Index: 6659300 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19