Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0962. Min Range: -12.0962
Max Act: 12.0962. Min Act: -0.1700
Data Index: 4674207 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.5337. Min Act: -0.1700
Data Index: 3396185 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.4712. Min Act: -0.1700
Data Index: 1357186 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.5337. Min Act: -0.1700
Data Index: 2274979 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.4087. Min Act: -0.1700
Data Index: 1608112 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.4087. Min Act: -0.1700
Data Index: 2483248 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.3462. Min Act: -0.1700
Data Index: 4168500 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.3462. Min Act: -0.1700
Data Index: 6273337 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.1587. Min Act: -0.1700
Data Index: 5719108 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.1587. Min Act: -0.1700
Data Index: 2843994 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.0337. Min Act: -0.1700
Data Index: 4931130 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.0337. Min Act: -0.1700
Data Index: 4339539 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.0337. Min Act: -0.1700
Data Index: 6317494 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0962. Min Range: -12.0962
Max Act: 10.9712. Min Act: -0.1700
Data Index: 7972341 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0962. Min Range: -12.0962
Max Act: 11.0337. Min Act: -0.1700
Data Index: 3035644 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0962. Min Range: -12.0962
Max Act: 10.9712. Min Act: -0.1700
Data Index: 5342949 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0962. Min Range: -12.0962
Max Act: 10.9712. Min Act: -0.1700
Data Index: 6534301 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0962. Min Range: -12.0962
Max Act: 10.9087. Min Act: -0.1700
Data Index: 8461807 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0962. Min Range: -12.0962
Max Act: 10.9087. Min Act: -0.1700
Data Index: 4284822 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0962. Min Range: -12.0962
Max Act: 10.8462. Min Act: -0.1700
Data Index: 3639105 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19