Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 816 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.7708. Min Act: -0.1700
Data Index: 1234246 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.7395. Min Act: -0.1700
Data Index: 5051210 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.7083. Min Act: -0.1700
Data Index: 881644 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.7083. Min Act: -0.1700
Data Index: 4762116 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.6458. Min Act: -0.1700
Data Index: 1097582 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.6458. Min Act: -0.1700
Data Index: 5131640 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.6145. Min Act: -0.1700
Data Index: 6692765 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.6458. Min Act: -0.1700
Data Index: 4092777 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.5520. Min Act: -0.1700
Data Index: 379572 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.5520. Min Act: -0.1700
Data Index: 7725925 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.5520. Min Act: -0.1700
Data Index: 6336815 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.5208. Min Act: -0.1700
Data Index: 2715369 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.5208. Min Act: -0.1700
Data Index: 3318100 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.4895. Min Act: -0.1700
Data Index: 2986050 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.4895. Min Act: -0.1700
Data Index: 523325 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.5208. Min Act: -0.1700
Data Index: 6064316 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.4583. Min Act: -0.1700
Data Index: 8342256 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.4583. Min Act: -0.1700
Data Index: 4931568 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.4583. Min Act: -0.1700
Data Index: 5826357 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7708. Min Range: -4.7708
Max Act: 4.4583. Min Act: -0.1700
Data Index: 5413201 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19