Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.5657. Min Act: -0.1700
Data Index: 8815461 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.5345. Min Act: -0.1700
Data Index: 2123237 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.3157. Min Act: -0.1700
Data Index: 3830809 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.2532. Min Act: -0.1700
Data Index: 5984973 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.2532. Min Act: -0.1700
Data Index: 1755504 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.1907. Min Act: -0.1700
Data Index: 7879144 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.2220. Min Act: -0.1700
Data Index: 6722314 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.1907. Min Act: -0.1700
Data Index: 6113337 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.1907. Min Act: -0.1700
Data Index: 3027949 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.1595. Min Act: -0.1700
Data Index: 2654561 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.1595. Min Act: -0.1700
Data Index: 3663863 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.1282. Min Act: -0.1700
Data Index: 1847515 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.1282. Min Act: -0.1700
Data Index: 6917229 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.1282. Min Act: -0.1700
Data Index: 900347 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.1282. Min Act: -0.1700
Data Index: 3522159 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.1282. Min Act: -0.1700
Data Index: 878392 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.1282. Min Act: -0.1700
Data Index: 8309248 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.1282. Min Act: -0.1700
Data Index: 3174090 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.0970. Min Act: -0.1700
Data Index: 7025822 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5657. Min Range: -6.5657
Max Act: 6.0657. Min Act: -0.1700
Data Index: 8749732 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19