Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.7622. Min Act: -0.1700
Data Index: 6385164 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.7622. Min Act: -0.1700
Data Index: 8317122 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.7309. Min Act: -0.1700
Data Index: 6411993 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6997. Min Act: -0.1700
Data Index: 2932019 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6997. Min Act: -0.1700
Data Index: 3951319 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6684. Min Act: -0.1700
Data Index: 1059723 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6684. Min Act: -0.1700
Data Index: 3855393 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6372. Min Act: -0.1700
Data Index: 112735 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6059. Min Act: -0.1700
Data Index: 6549877 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6059. Min Act: -0.1700
Data Index: 8054719 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6372. Min Act: -0.1700
Data Index: 2331250 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6059. Min Act: -0.1700
Data Index: 2283671 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6059. Min Act: -0.1700
Data Index: 3896621 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6059. Min Act: -0.1700
Data Index: 3668315 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6059. Min Act: -0.1700
Data Index: 5686737 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.6059. Min Act: -0.1700
Data Index: 3064445 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.5434. Min Act: -0.1700
Data Index: 924008 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.5747. Min Act: -0.1700
Data Index: 820509 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.5747. Min Act: -0.1700
Data Index: 5483505 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7622. Min Range: -5.7622
Max Act: 5.5747. Min Act: -0.1700
Data Index: 2748168 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19