Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2677 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0072. Min Range: -8.0072
Max Act: 8.0072. Min Act: -0.1700
Data Index: 7295912 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.7259. Min Act: -0.1700
Data Index: 8526751 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.6947. Min Act: -0.1700
Data Index: 3936650 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.6634. Min Act: -0.1700
Data Index: 6791915 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.6634. Min Act: -0.1700
Data Index: 371009 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.6009. Min Act: -0.1700
Data Index: 8214113 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.4759. Min Act: -0.1700
Data Index: 5306346 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.4447. Min Act: -0.1700
Data Index: 7921643 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.3822. Min Act: -0.1700
Data Index: 3004883 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.2884. Min Act: -0.1700
Data Index: 4084942 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.2572. Min Act: -0.1700
Data Index: 6534353 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.2259. Min Act: -0.1700
Data Index: 5472402 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.1947. Min Act: -0.1700
Data Index: 3092542 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.1947. Min Act: -0.1700
Data Index: 8742667 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.1947. Min Act: -0.1700
Data Index: 7180318 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.1947. Min Act: -0.1700
Data Index: 1404290 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.1634. Min Act: -0.1700
Data Index: 2555720 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.1322. Min Act: -0.1700
Data Index: 3110067 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.1322. Min Act: -0.1700
Data Index: 2294451 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0072. Min Range: -8.0072
Max Act: 7.1322. Min Act: -0.1700
Data Index: 6135692 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19