Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3742 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.9935. Min Act: -0.1700
Data Index: 5277401 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.9623. Min Act: -0.1700
Data Index: 7120778 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.9623. Min Act: -0.1700
Data Index: 2636526 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.9623. Min Act: -0.1700
Data Index: 1805889 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.9310. Min Act: -0.1700
Data Index: 5540750 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.9310. Min Act: -0.1700
Data Index: 3276546 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8998. Min Act: -0.1700
Data Index: 2767734 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8998. Min Act: -0.1700
Data Index: 5621801 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8998. Min Act: -0.1700
Data Index: 2188078 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8685. Min Act: -0.1700
Data Index: 6986311 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8373. Min Act: -0.1700
Data Index: 3729095 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8373. Min Act: -0.1700
Data Index: 4431135 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8373. Min Act: -0.1700
Data Index: 7723976 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8060. Min Act: -0.1700
Data Index: 1559799 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8060. Min Act: -0.1700
Data Index: 767767 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8060. Min Act: -0.1700
Data Index: 1630701 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8060. Min Act: -0.1700
Data Index: 2608293 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8060. Min Act: -0.1700
Data Index: 6389108 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8373. Min Act: -0.1700
Data Index: 3014381 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9935. Min Range: -4.9935
Max Act: 4.8060. Min Act: -0.1700
Data Index: 1087115 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19