Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5511 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.8706. Min Act: -0.1700
Data Index: 387643 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.8393. Min Act: -0.1700
Data Index: 1461008 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.8393. Min Act: -0.1700
Data Index: 4383550 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.8080. Min Act: -0.1700
Data Index: 4778888 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.8080. Min Act: -0.1700
Data Index: 5314270 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.8080. Min Act: -0.1700
Data Index: 2240591 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.8080. Min Act: -0.1700
Data Index: 7834659 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.8080. Min Act: -0.1700
Data Index: 3460788 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.8080. Min Act: -0.1700
Data Index: 8240922 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.8080. Min Act: -0.1700
Data Index: 1665392 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.7767. Min Act: -0.1700
Data Index: 4448738 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.7767. Min Act: -0.1700
Data Index: 613379 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.7767. Min Act: -0.1700
Data Index: 4136988 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.7767. Min Act: -0.1700
Data Index: 1613142 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.7767. Min Act: -0.1700
Data Index: 3388327 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.7767. Min Act: -0.1700
Data Index: 6539152 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.7767. Min Act: -0.1700
Data Index: 4865047 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.7455. Min Act: -0.1700
Data Index: 3895306 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.7455. Min Act: -0.1700
Data Index: 1829112 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8706. Min Range: -3.8706
Max Act: 3.7455. Min Act: -0.1700
Data Index: 2147956 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19