Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 625 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3341. Min Range: -8.3341
Max Act: 8.3341. Min Act: -0.1700
Data Index: 8289641 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3341. Min Range: -8.3341
Max Act: 8.2091. Min Act: -0.1700
Data Index: 8258042 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3341. Min Range: -8.3341
Max Act: 8.1466. Min Act: -0.1700
Data Index: 438857 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3341. Min Range: -8.3341
Max Act: 8.1466. Min Act: -0.1700
Data Index: 3099566 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3341. Min Range: -8.3341
Max Act: 8.0841. Min Act: -0.1700
Data Index: 849595 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.9591. Min Act: -0.1700
Data Index: 4163570 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.9591. Min Act: -0.1700
Data Index: 3436356 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.9591. Min Act: -0.1700
Data Index: 1189114 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.9591. Min Act: -0.1700
Data Index: 3099567 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.9591. Min Act: -0.1700
Data Index: 103740 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.9591. Min Act: -0.1700
Data Index: 2256864 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.9591. Min Act: -0.1700
Data Index: 8226828 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.9591. Min Act: -0.1700
Data Index: 5541692 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.9591. Min Act: -0.1700
Data Index: 4181944 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.9591. Min Act: -0.1700
Data Index: 2431771 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.9591. Min Act: -0.1700
Data Index: 3711295 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.8966. Min Act: -0.1700
Data Index: 425877 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.8966. Min Act: -0.1700
Data Index: 1614288 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.8966. Min Act: -0.1700
Data Index: 2468913 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3341. Min Range: -8.3341
Max Act: 7.9591. Min Act: -0.1700
Data Index: 4881628 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19