Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1471. Min Range: -4.1471
Max Act: 4.1471. Min Act: -0.1700
Data Index: 6452267 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.9908. Min Act: -0.1700
Data Index: 1905480 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.9596. Min Act: -0.1700
Data Index: 8206545 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.9596. Min Act: -0.1700
Data Index: 239632 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.8970. Min Act: -0.1700
Data Index: 239628 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.8970. Min Act: -0.1700
Data Index: 2617780 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.8658. Min Act: -0.1700
Data Index: 8538717 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.8658. Min Act: -0.1700
Data Index: 239636 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.8032. Min Act: -0.1700
Data Index: 2794414 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.8345. Min Act: -0.1700
Data Index: 7675621 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.8345. Min Act: -0.1700
Data Index: 3756433 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.7719. Min Act: -0.1700
Data Index: 4608265 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.8032. Min Act: -0.1700
Data Index: 283680 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.8032. Min Act: -0.1700
Data Index: 6765348 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.8345. Min Act: -0.1700
Data Index: 239635 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.7719. Min Act: -0.1700
Data Index: 758130 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.7719. Min Act: -0.1700
Data Index: 2794416 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.7719. Min Act: -0.1700
Data Index: 2782200 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.7719. Min Act: -0.1700
Data Index: 5245354 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1471. Min Range: -4.1471
Max Act: 3.7719. Min Act: -0.1700
Data Index: 7520433 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19