Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.4831. Min Act: -0.1700
Data Index: 8743716 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.4518. Min Act: -0.1700
Data Index: 4868694 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.4206. Min Act: -0.1700
Data Index: 8743718 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.3893. Min Act: -0.1700
Data Index: 6877703 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.3581. Min Act: -0.1700
Data Index: 7306147 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.3268. Min Act: -0.1700
Data Index: 8743717 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.3268. Min Act: -0.1700
Data Index: 8743719 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.3268. Min Act: -0.1700
Data Index: 3855689 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.2956. Min Act: -0.1700
Data Index: 988140 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.2956. Min Act: -0.1700
Data Index: 6998068 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.2643. Min Act: -0.1700
Data Index: 7695726 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.2331. Min Act: -0.1700
Data Index: 4094332 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.2643. Min Act: -0.1700
Data Index: 6998066 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.2018. Min Act: -0.1700
Data Index: 1998343 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.1706. Min Act: -0.1700
Data Index: 8548693 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.2018. Min Act: -0.1700
Data Index: 4096301 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.2018. Min Act: -0.1700
Data Index: 1785478 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.2018. Min Act: -0.1700
Data Index: 1047256 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.2018. Min Act: -0.1700
Data Index: 8738459 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4831. Min Range: -4.4831
Max Act: 4.2018. Min Act: -0.1700
Data Index: 196661 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19