Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3972 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.7958. Min Act: -0.1700
Data Index: 2414116 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.6708. Min Act: -0.1700
Data Index: 1064114 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.6083. Min Act: -0.1700
Data Index: 7216896 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.5771. Min Act: -0.1700
Data Index: 4207764 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.5771. Min Act: -0.1700
Data Index: 5440377 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.5458. Min Act: -0.1700
Data Index: 5242292 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.5458. Min Act: -0.1700
Data Index: 6938854 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.5458. Min Act: -0.1700
Data Index: 6889776 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.5771. Min Act: -0.1700
Data Index: 5489837 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.5458. Min Act: -0.1700
Data Index: 38792 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.5458. Min Act: -0.1700
Data Index: 2914091 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.5146. Min Act: -0.1700
Data Index: 5029278 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.5146. Min Act: -0.1700
Data Index: 3541424 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.4833. Min Act: -0.1700
Data Index: 8814703 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.4833. Min Act: -0.1700
Data Index: 6774105 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.4833. Min Act: -0.1700
Data Index: 3773743 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.4833. Min Act: -0.1700
Data Index: 4746403 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.4833. Min Act: -0.1700
Data Index: 8300015 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.4521. Min Act: -0.1700
Data Index: 5779836 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7958. Min Range: -4.7958
Max Act: 4.4521. Min Act: -0.1700
Data Index: 2246930 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19