Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1114 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.6744. Min Act: -0.1700
Data Index: 2083177 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.6422. Min Act: -0.1700
Data Index: 8335476 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.6342. Min Act: -0.1700
Data Index: 5580733 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.6422. Min Act: -0.1700
Data Index: 2408721 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.6262. Min Act: -0.1700
Data Index: 4652640 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.6104. Min Act: -0.1700
Data Index: 2533430 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.6025. Min Act: -0.1700
Data Index: 8604162 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.6025. Min Act: -0.1700
Data Index: 3826053 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.6025. Min Act: -0.1700
Data Index: 7722076 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.5946. Min Act: -0.1700
Data Index: 1783576 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.6025. Min Act: -0.1700
Data Index: 4060901 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.5946. Min Act: -0.1700
Data Index: 8403547 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.5868. Min Act: -0.1700
Data Index: 8424931 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.5868. Min Act: -0.1700
Data Index: 7628306 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.5868. Min Act: -0.1700
Data Index: 1428890 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.5790. Min Act: -0.1700
Data Index: 5015434 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.5868. Min Act: -0.1700
Data Index: 6534379 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.5790. Min Act: -0.1700
Data Index: 3972902 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.5790. Min Act: -0.1700
Data Index: 6403890 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6744. Min Range: -0.6744
Max Act: 0.5790. Min Act: -0.1700
Data Index: 633666 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19