Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2963 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.8186. Min Act: -0.1700
Data Index: 6416354 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.7874. Min Act: -0.1700
Data Index: 1078479 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.7561. Min Act: -0.1700
Data Index: 2032658 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.7561. Min Act: -0.1700
Data Index: 4362559 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.7561. Min Act: -0.1700
Data Index: 6887028 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.7249. Min Act: -0.1700
Data Index: 7376094 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.7249. Min Act: -0.1700
Data Index: 5778612 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.6311. Min Act: -0.1700
Data Index: 5038642 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.6311. Min Act: -0.1700
Data Index: 186914 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.5999. Min Act: -0.1700
Data Index: 5586781 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.6311. Min Act: -0.1700
Data Index: 605776 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.5374. Min Act: -0.1700
Data Index: 7717162 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.5374. Min Act: -0.1700
Data Index: 1401163 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.5374. Min Act: -0.1700
Data Index: 6390667 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.5061. Min Act: -0.1700
Data Index: 2738063 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.5061. Min Act: -0.1700
Data Index: 1617634 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.5061. Min Act: -0.1700
Data Index: 4705986 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.4749. Min Act: -0.1700
Data Index: 2383821 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.4749. Min Act: -0.1700
Data Index: 5145391 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8186. Min Range: -5.8186
Max Act: 5.4749. Min Act: -0.1700
Data Index: 4662122 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19