Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3041 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.7074. Min Act: -0.1700
Data Index: 6409925 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.6761. Min Act: -0.1700
Data Index: 2285048 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.6761. Min Act: -0.1700
Data Index: 8030791 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.6761. Min Act: -0.1700
Data Index: 7535015 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.6761. Min Act: -0.1700
Data Index: 7301102 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.6761. Min Act: -0.1700
Data Index: 5609845 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.6761. Min Act: -0.1700
Data Index: 5519764 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.6761. Min Act: -0.1700
Data Index: 767225 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.6761. Min Act: -0.1700
Data Index: 1241998 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.6761. Min Act: -0.1700
Data Index: 5207589 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.6761. Min Act: -0.1700
Data Index: 1722864 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.6292. Min Act: -0.1700
Data Index: 4021925 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.5666. Min Act: -0.1700
Data Index: 452739 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.5666. Min Act: -0.1700
Data Index: 1074985 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.5666. Min Act: -0.1700
Data Index: 893923 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.5666. Min Act: -0.1700
Data Index: 1039428 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.5666. Min Act: -0.1700
Data Index: 673940 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.5666. Min Act: -0.1700
Data Index: 682357 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.5666. Min Act: -0.1700
Data Index: 365997 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7074. Min Range: -3.7074
Max Act: 3.5666. Min Act: -0.1700
Data Index: 317597 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19