Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1608 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.9573. Min Act: -0.1700
Data Index: 3644157 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.9886. Min Act: -0.1700
Data Index: 5318012 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.9573. Min Act: -0.1700
Data Index: 7118311 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.9886. Min Act: -0.1700
Data Index: 3493275 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.9261. Min Act: -0.1700
Data Index: 3898927 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.8948. Min Act: -0.1700
Data Index: 4485245 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.9573. Min Act: -0.1700
Data Index: 5714984 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.9261. Min Act: -0.1700
Data Index: 8406807 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.9261. Min Act: -0.1700
Data Index: 6673406 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.9261. Min Act: -0.1700
Data Index: 6370697 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.8948. Min Act: -0.1700
Data Index: 432937 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.8948. Min Act: -0.1700
Data Index: 172815 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.8948. Min Act: -0.1700
Data Index: 884587 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.8636. Min Act: -0.1700
Data Index: 5553132 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.8948. Min Act: -0.1700
Data Index: 4474341 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.8636. Min Act: -0.1700
Data Index: 5118573 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.8948. Min Act: -0.1700
Data Index: 2199399 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.8323. Min Act: -0.1700
Data Index: 4539606 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.8636. Min Act: -0.1700
Data Index: 3866394 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9886. Min Range: -4.9886
Max Act: 4.8636. Min Act: -0.1700
Data Index: 2122763 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19