Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2769 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.8435. Min Act: -0.1700
Data Index: 768840 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.6560. Min Act: -0.1700
Data Index: 1326145 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.4685. Min Act: -0.1700
Data Index: 4975492 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.4060. Min Act: -0.1700
Data Index: 7482622 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.4060. Min Act: -0.1700
Data Index: 3405652 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.4060. Min Act: -0.1700
Data Index: 7147176 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.3435. Min Act: -0.1700
Data Index: 594454 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.3435. Min Act: -0.1700
Data Index: 8273777 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.3435. Min Act: -0.1700
Data Index: 1755727 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.3435. Min Act: -0.1700
Data Index: 1217852 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.2810. Min Act: -0.1700
Data Index: 4404954 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.3435. Min Act: -0.1700
Data Index: 5307226 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.3435. Min Act: -0.1700
Data Index: 4414967 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.2810. Min Act: -0.1700
Data Index: 8095943 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.2810. Min Act: -0.1700
Data Index: 6350770 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.2185. Min Act: -0.1700
Data Index: 5824792 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.2185. Min Act: -0.1700
Data Index: 4282073 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.1560. Min Act: -0.1700
Data Index: 2001925 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.2185. Min Act: -0.1700
Data Index: 2697758 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8435. Min Range: -10.8435
Max Act: 10.2185. Min Act: -0.1700
Data Index: 2146952 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19