Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 377 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.8247. Min Act: -0.1700
Data Index: 7611165 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.8088. Min Act: -0.1700
Data Index: 4482250 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7929. Min Act: -0.1700
Data Index: 3147523 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7929. Min Act: -0.1700
Data Index: 7084351 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7769. Min Act: -0.1700
Data Index: 1754404 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7610. Min Act: -0.1700
Data Index: 760694 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7450. Min Act: -0.1700
Data Index: 8390910 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7450. Min Act: -0.1700
Data Index: 5778317 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7450. Min Act: -0.1700
Data Index: 1980791 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7769. Min Act: -0.1700
Data Index: 1278424 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7450. Min Act: -0.1700
Data Index: 1288222 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7290. Min Act: -0.1700
Data Index: 1919787 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7450. Min Act: -0.1700
Data Index: 4710385 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7450. Min Act: -0.1700
Data Index: 5854436 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7450. Min Act: -0.1700
Data Index: 6789462 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7131. Min Act: -0.1700
Data Index: 668503 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7131. Min Act: -0.1700
Data Index: 3077485 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.6971. Min Act: -0.1700
Data Index: 2846653 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.6810. Min Act: -0.1700
Data Index: 8810906 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8247. Min Range: -2.8247
Max Act: 2.7131. Min Act: -0.1700
Data Index: 5002005 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19