Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 329 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 2261253 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 4331785 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 6478791 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 5027062 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 6417125 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 8133937 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 7634528 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 2853691 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 5995965 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 2542785 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 963557 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 5951720 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 7750765 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 6478785 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 5251961 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 5245020 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 2725187 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5805. Min Act: -0.1700
Data Index: 131163 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.5483. Min Act: -0.1700
Data Index: 713678 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5805. Min Range: -2.5805
Max Act: 2.4998. Min Act: -0.1700
Data Index: 3371188 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19