Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.9083. Min Act: -0.1700
Data Index: 4477964 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.8925. Min Act: -0.1700
Data Index: 7137276 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.8766. Min Act: -0.1700
Data Index: 818978 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.8607. Min Act: -0.1700
Data Index: 3992806 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.8290. Min Act: -0.1700
Data Index: 2784432 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.8290. Min Act: -0.1700
Data Index: 1373767 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.8290. Min Act: -0.1700
Data Index: 8765180 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.8290. Min Act: -0.1700
Data Index: 6192234 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.8130. Min Act: -0.1700
Data Index: 7350907 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.8130. Min Act: -0.1700
Data Index: 8147472 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.7971. Min Act: -0.1700
Data Index: 734653 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.7971. Min Act: -0.1700
Data Index: 6747885 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.7971. Min Act: -0.1700
Data Index: 4601008 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.8130. Min Act: -0.1700
Data Index: 1857842 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.7971. Min Act: -0.1700
Data Index: 5360140 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.7971. Min Act: -0.1700
Data Index: 7406743 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.7971. Min Act: -0.1700
Data Index: 2558911 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.7971. Min Act: -0.1700
Data Index: 7977258 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.7971. Min Act: -0.1700
Data Index: 117541 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9083. Min Range: -2.9083
Max Act: 2.7971. Min Act: -0.1700
Data Index: 3294348 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19