Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3116 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0698. Min Range: -7.0698
Max Act: 7.0698. Min Act: -0.1700
Data Index: 4751442 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.7885. Min Act: -0.1700
Data Index: 6791080 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.6635. Min Act: -0.1700
Data Index: 8590451 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.6323. Min Act: -0.1700
Data Index: 3077197 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.5073. Min Act: -0.1700
Data Index: 5123035 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.5385. Min Act: -0.1700
Data Index: 2343834 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.4760. Min Act: -0.1700
Data Index: 2441872 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.5073. Min Act: -0.1700
Data Index: 3604461 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.4448. Min Act: -0.1700
Data Index: 4572010 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.4448. Min Act: -0.1700
Data Index: 5101365 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3823. Min Act: -0.1700
Data Index: 4723680 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3823. Min Act: -0.1700
Data Index: 4674394 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3198. Min Act: -0.1700
Data Index: 8322169 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3198. Min Act: -0.1700
Data Index: 7161713 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3510. Min Act: -0.1700
Data Index: 8112885 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3198. Min Act: -0.1700
Data Index: 71597 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3510. Min Act: -0.1700
Data Index: 4247489 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3510. Min Act: -0.1700
Data Index: 1617162 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3198. Min Act: -0.1700
Data Index: 4583468 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0698. Min Range: -7.0698
Max Act: 6.3198. Min Act: -0.1700
Data Index: 2313960 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19