Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4827 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0352. Min Range: -8.0352
Max Act: 8.0352. Min Act: -0.1700
Data Index: 2170280 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0352. Min Range: -8.0352
Max Act: 8.0040. Min Act: -0.1700
Data Index: 2170272 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.9415. Min Act: -0.1700
Data Index: 2170278 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 7253437 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 600726 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 7657278 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 1666315 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.7852. Min Act: -0.1700
Data Index: 1627536 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 7253441 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 1582051 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 1582049 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 7253439 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 6452811 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.7852. Min Act: -0.1700
Data Index: 1123951 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 6452809 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 5620589 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 2768803 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 2768799 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 2491451 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0352. Min Range: -8.0352
Max Act: 7.8165. Min Act: -0.1700
Data Index: 600724 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19