Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4971 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.8624. Min Act: -0.1700
Data Index: 8602870 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.7687. Min Act: -0.1700
Data Index: 4823350 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.7062. Min Act: -0.1700
Data Index: 8488078 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.7062. Min Act: -0.1700
Data Index: 910313 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.6749. Min Act: -0.1700
Data Index: 1517822 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.6124. Min Act: -0.1700
Data Index: 2103051 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.5812. Min Act: -0.1700
Data Index: 108877 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.5499. Min Act: -0.1700
Data Index: 4565828 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.5499. Min Act: -0.1700
Data Index: 1411784 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.5187. Min Act: -0.1700
Data Index: 2179778 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.5187. Min Act: -0.1700
Data Index: 7774205 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.5187. Min Act: -0.1700
Data Index: 6971483 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.5187. Min Act: -0.1700
Data Index: 3929022 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.5187. Min Act: -0.1700
Data Index: 5225786 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.5187. Min Act: -0.1700
Data Index: 3432717 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.5187. Min Act: -0.1700
Data Index: 6766281 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.5187. Min Act: -0.1700
Data Index: 3988568 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.4874. Min Act: -0.1700
Data Index: 2840896 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.4874. Min Act: -0.1700
Data Index: 6835862 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8624. Min Range: -5.8624
Max Act: 5.4874. Min Act: -0.1700
Data Index: 5759084 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19