Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1706 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.9438. Min Act: -0.1700
Data Index: 1439319 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.8813. Min Act: -0.1700
Data Index: 7618571 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.8188. Min Act: -0.1700
Data Index: 7975244 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.7563. Min Act: -0.1700
Data Index: 7836791 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.7563. Min Act: -0.1700
Data Index: 6993982 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.7563. Min Act: -0.1700
Data Index: 6697674 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.6938. Min Act: -0.1700
Data Index: 726294 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.6313. Min Act: -0.1700
Data Index: 5367662 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.5688. Min Act: -0.1700
Data Index: 6469443 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.5688. Min Act: -0.1700
Data Index: 184735 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.5063. Min Act: -0.1700
Data Index: 1346707 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.5063. Min Act: -0.1700
Data Index: 2677487 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.5063. Min Act: -0.1700
Data Index: 6445129 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.4438. Min Act: -0.1700
Data Index: 8166028 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.4438. Min Act: -0.1700
Data Index: 5609699 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.4438. Min Act: -0.1700
Data Index: 7159174 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.4438. Min Act: -0.1700
Data Index: 1880418 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.4438. Min Act: -0.1700
Data Index: 2334324 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.4126. Min Act: -0.1700
Data Index: 4498072 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9438. Min Range: -7.9438
Max Act: 7.3813. Min Act: -0.1700
Data Index: 7505959 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19