Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5746 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0954. Min Range: -7.0954
Max Act: 7.0954. Min Act: -0.1700
Data Index: 464498 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0954. Min Range: -7.0954
Max Act: 7.0642. Min Act: -0.1700
Data Index: 5309773 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.9079. Min Act: -0.1700
Data Index: 2422805 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.6892. Min Act: -0.1700
Data Index: 572122 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.6267. Min Act: -0.1700
Data Index: 3895703 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.6267. Min Act: -0.1700
Data Index: 5873500 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.6267. Min Act: -0.1700
Data Index: 819304 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.5954. Min Act: -0.1700
Data Index: 6860847 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.5329. Min Act: -0.1700
Data Index: 7269135 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.5329. Min Act: -0.1700
Data Index: 3290971 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.5329. Min Act: -0.1700
Data Index: 8358834 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.5017. Min Act: -0.1700
Data Index: 5861474 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.5017. Min Act: -0.1700
Data Index: 5108678 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.5017. Min Act: -0.1700
Data Index: 793118 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.4704. Min Act: -0.1700
Data Index: 3811254 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.4704. Min Act: -0.1700
Data Index: 7541693 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.4704. Min Act: -0.1700
Data Index: 2384766 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.4392. Min Act: -0.1700
Data Index: 1523343 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.4079. Min Act: -0.1700
Data Index: 1531301 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.4079. Min Act: -0.1700
Data Index: 273375 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19