Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4417 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1233. Min Range: -7.1233
Max Act: 7.1233. Min Act: -0.1700
Data Index: 2569971 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1233. Min Range: -7.1233
Max Act: 7.0608. Min Act: -0.1700
Data Index: 1708270 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1233. Min Range: -7.1233
Max Act: 7.0608. Min Act: -0.1700
Data Index: 7986895 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1233. Min Range: -7.1233
Max Act: 7.0608. Min Act: -0.1700
Data Index: 1708271 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.9983. Min Act: -0.1700
Data Index: 1708265 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.9983. Min Act: -0.1700
Data Index: 1708273 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.9983. Min Act: -0.1700
Data Index: 7384376 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.9983. Min Act: -0.1700
Data Index: 1708263 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.9983. Min Act: -0.1700
Data Index: 7384377 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.9983. Min Act: -0.1700
Data Index: 486833 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.9358. Min Act: -0.1700
Data Index: 7240010 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.9358. Min Act: -0.1700
Data Index: 6753062 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.9358. Min Act: -0.1700
Data Index: 6237984 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.8733. Min Act: -0.1700
Data Index: 5167280 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.9358. Min Act: -0.1700
Data Index: 1708269 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.9358. Min Act: -0.1700
Data Index: 1708272 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.8733. Min Act: -0.1700
Data Index: 1701669 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.8733. Min Act: -0.1700
Data Index: 1708268 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.8733. Min Act: -0.1700
Data Index: 3657026 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1233. Min Range: -7.1233
Max Act: 6.8108. Min Act: -0.1700
Data Index: 2644504 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19