Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4330 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.8900. Min Act: -0.1700
Data Index: 6975152 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.8900. Min Act: -0.1700
Data Index: 7290479 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.7025. Min Act: -0.1700
Data Index: 1784616 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.7025. Min Act: -0.1700
Data Index: 3572334 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.6400. Min Act: -0.1700
Data Index: 7682696 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.5775. Min Act: -0.1700
Data Index: 8035079 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.5775. Min Act: -0.1700
Data Index: 3425377 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.5150. Min Act: -0.1700
Data Index: 6822966 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.5150. Min Act: -0.1700
Data Index: 2174242 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.4837. Min Act: -0.1700
Data Index: 5017514 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.4837. Min Act: -0.1700
Data Index: 7368093 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.4525. Min Act: -0.1700
Data Index: 2299685 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.4837. Min Act: -0.1700
Data Index: 8772254 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.4212. Min Act: -0.1700
Data Index: 5585229 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.4212. Min Act: -0.1700
Data Index: 7917695 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.3587. Min Act: -0.1700
Data Index: 8767899 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.3900. Min Act: -0.1700
Data Index: 6525141 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.3900. Min Act: -0.1700
Data Index: 6518509 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.3900. Min Act: -0.1700
Data Index: 4760310 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8900. Min Range: -7.8900
Max Act: 7.3275. Min Act: -0.1700
Data Index: 135757 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19