Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.9913. Min Act: -0.1700
Data Index: 5234748 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.9913. Min Act: -0.1700
Data Index: 2514352 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8975. Min Act: -0.1700
Data Index: 4006078 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8975. Min Act: -0.1700
Data Index: 2558619 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8975. Min Act: -0.1700
Data Index: 675297 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8975. Min Act: -0.1700
Data Index: 7022188 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8663. Min Act: -0.1700
Data Index: 4023829 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8663. Min Act: -0.1700
Data Index: 7774499 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8350. Min Act: -0.1700
Data Index: 732682 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8350. Min Act: -0.1700
Data Index: 7341197 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8663. Min Act: -0.1700
Data Index: 3931517 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8350. Min Act: -0.1700
Data Index: 3851404 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8038. Min Act: -0.1700
Data Index: 8534702 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8038. Min Act: -0.1700
Data Index: 5483323 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8038. Min Act: -0.1700
Data Index: 4027602 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8038. Min Act: -0.1700
Data Index: 2223243 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.8038. Min Act: -0.1700
Data Index: 4360581 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.7725. Min Act: -0.1700
Data Index: 4165224 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.7725. Min Act: -0.1700
Data Index: 5359439 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9913. Min Range: -4.9913
Max Act: 4.7725. Min Act: -0.1700
Data Index: 1596541 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19