Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1364 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6048. Min Range: -6.6048
Max Act: 6.6048. Min Act: -0.1700
Data Index: 1456115 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6048. Min Range: -6.6048
Max Act: 6.2298. Min Act: -0.1700
Data Index: 2882493 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6048. Min Range: -6.6048
Max Act: 6.0423. Min Act: -0.1700
Data Index: 8185604 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.9485. Min Act: -0.1700
Data Index: 1218984 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.9173. Min Act: -0.1700
Data Index: 80329 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.9173. Min Act: -0.1700
Data Index: 6848076 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.8548. Min Act: -0.1700
Data Index: 2979678 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.8548. Min Act: -0.1700
Data Index: 1944977 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.7923. Min Act: -0.1700
Data Index: 2072031 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.7923. Min Act: -0.1700
Data Index: 5616274 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.7610. Min Act: -0.1700
Data Index: 3978192 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.7610. Min Act: -0.1700
Data Index: 3307576 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.7610. Min Act: -0.1700
Data Index: 6862063 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.7610. Min Act: -0.1700
Data Index: 3753138 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.7298. Min Act: -0.1700
Data Index: 5749178 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.6673. Min Act: -0.1700
Data Index: 34780 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.6673. Min Act: -0.1700
Data Index: 3287148 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.6673. Min Act: -0.1700
Data Index: 4728965 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.6985. Min Act: -0.1700
Data Index: 7079865 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6048. Min Range: -6.6048
Max Act: 5.6673. Min Act: -0.1700
Data Index: 4639750 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19