Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1733 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.8257. Min Act: -0.1700
Data Index: 6831421 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.7007. Min Act: -0.1700
Data Index: 7377482 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.6695. Min Act: -0.1700
Data Index: 8722822 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.5445. Min Act: -0.1700
Data Index: 7690864 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.5132. Min Act: -0.1700
Data Index: 5555019 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.5132. Min Act: -0.1700
Data Index: 5821853 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.5132. Min Act: -0.1700
Data Index: 8057791 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.5132. Min Act: -0.1700
Data Index: 2784286 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.5132. Min Act: -0.1700
Data Index: 593770 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.4507. Min Act: -0.1700
Data Index: 3304701 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.4195. Min Act: -0.1700
Data Index: 3618483 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.3882. Min Act: -0.1700
Data Index: 8105729 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.4195. Min Act: -0.1700
Data Index: 2832082 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.4195. Min Act: -0.1700
Data Index: 4078349 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.4195. Min Act: -0.1700
Data Index: 5170443 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.3882. Min Act: -0.1700
Data Index: 5821886 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.3882. Min Act: -0.1700
Data Index: 832392 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.3882. Min Act: -0.1700
Data Index: 1803787 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.3570. Min Act: -0.1700
Data Index: 1742788 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8257. Min Range: -5.8257
Max Act: 5.4195. Min Act: -0.1700
Data Index: 6158730 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19