Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0313. Min Range: -7.0313
Max Act: 7.0313. Min Act: -0.1700
Data Index: 2692196 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.8750. Min Act: -0.1700
Data Index: 3892027 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.8125. Min Act: -0.1700
Data Index: 5817684 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.7813. Min Act: -0.1700
Data Index: 8235686 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.7500. Min Act: -0.1700
Data Index: 2288366 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.7188. Min Act: -0.1700
Data Index: 1288401 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.7188. Min Act: -0.1700
Data Index: 8133069 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.7188. Min Act: -0.1700
Data Index: 4866995 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.7188. Min Act: -0.1700
Data Index: 2261360 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.6875. Min Act: -0.1700
Data Index: 5331278 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.6875. Min Act: -0.1700
Data Index: 393672 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.6563. Min Act: -0.1700
Data Index: 5268159 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.5938. Min Act: -0.1700
Data Index: 4763707 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.6250. Min Act: -0.1700
Data Index: 3031398 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.6250. Min Act: -0.1700
Data Index: 3361673 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.6250. Min Act: -0.1700
Data Index: 7524688 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.6250. Min Act: -0.1700
Data Index: 3852672 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.5625. Min Act: -0.1700
Data Index: 4435483 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.5938. Min Act: -0.1700
Data Index: 557533 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0313. Min Range: -7.0313
Max Act: 6.5625. Min Act: -0.1700
Data Index: 6212013 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19