Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5199 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.7776. Min Act: -0.1700
Data Index: 4990477 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6998. Min Act: -0.1700
Data Index: 5535245 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6912. Min Act: -0.1700
Data Index: 6474793 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6738. Min Act: -0.1700
Data Index: 2210100 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6738. Min Act: -0.1700
Data Index: 7214959 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6651. Min Act: -0.1700
Data Index: 3237041 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 1726451 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 1750572 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 3744227 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 1133963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 2331613 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 1582635 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 5892736 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 4019758 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 434017 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 4147998 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 1973441 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 5362357 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 893494 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7776. Min Range: -1.7776
Max Act: 1.6564. Min Act: -0.1700
Data Index: 576719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19