Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5427 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.7650. Min Act: -0.1700
Data Index: 5016356 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.7025. Min Act: -0.1700
Data Index: 5298737 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.7025. Min Act: -0.1700
Data Index: 5603909 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.6713. Min Act: -0.1700
Data Index: 5808256 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.6088. Min Act: -0.1700
Data Index: 7220762 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.6713. Min Act: -0.1700
Data Index: 6441224 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.6088. Min Act: -0.1700
Data Index: 426734 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.6088. Min Act: -0.1700
Data Index: 5373264 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.6088. Min Act: -0.1700
Data Index: 1432510 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.6088. Min Act: -0.1700
Data Index: 2128794 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.5775. Min Act: -0.1700
Data Index: 5113902 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.5775. Min Act: -0.1700
Data Index: 426735 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.5775. Min Act: -0.1700
Data Index: 774417 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.5775. Min Act: -0.1700
Data Index: 4624231 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.5775. Min Act: -0.1700
Data Index: 7732984 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.5463. Min Act: -0.1700
Data Index: 426737 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.5463. Min Act: -0.1700
Data Index: 933091 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.5463. Min Act: -0.1700
Data Index: 50213 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.5150. Min Act: -0.1700
Data Index: 1770407 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.5150. Min Act: -0.1700
Data Index: 4965870 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19