Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4930 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.5724. Min Act: -0.1700
Data Index: 8606527 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.5412. Min Act: -0.1700
Data Index: 1815790 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.5412. Min Act: -0.1700
Data Index: 7164117 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.5099. Min Act: -0.1700
Data Index: 6330521 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.5412. Min Act: -0.1700
Data Index: 6184622 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.5099. Min Act: -0.1700
Data Index: 8280109 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.4162. Min Act: -0.1700
Data Index: 3321732 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.4162. Min Act: -0.1700
Data Index: 2386903 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.4162. Min Act: -0.1700
Data Index: 454678 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.3849. Min Act: -0.1700
Data Index: 7649279 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.3849. Min Act: -0.1700
Data Index: 806126 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.3537. Min Act: -0.1700
Data Index: 417086 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.3537. Min Act: -0.1700
Data Index: 3950798 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.3537. Min Act: -0.1700
Data Index: 4666980 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.3224. Min Act: -0.1700
Data Index: 6304590 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.3224. Min Act: -0.1700
Data Index: 102205 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.3224. Min Act: -0.1700
Data Index: 4779446 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.2912. Min Act: -0.1700
Data Index: 6731517 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.2599. Min Act: -0.1700
Data Index: 7615148 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5724. Min Range: -6.5724
Max Act: 6.2599. Min Act: -0.1700
Data Index: 4458862 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19