Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4939 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3812. Min Range: -6.3812
Max Act: 6.3812. Min Act: -0.1700
Data Index: 6938401 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3812. Min Range: -6.3812
Max Act: 6.0687. Min Act: -0.1700
Data Index: 1382761 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.9749. Min Act: -0.1700
Data Index: 564677 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.9749. Min Act: -0.1700
Data Index: 4532066 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.9437. Min Act: -0.1700
Data Index: 6260962 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.9124. Min Act: -0.1700
Data Index: 8240427 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.9124. Min Act: -0.1700
Data Index: 8694692 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.8499. Min Act: -0.1700
Data Index: 3675260 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.8812. Min Act: -0.1700
Data Index: 1886230 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.8812. Min Act: -0.1700
Data Index: 516012 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.8812. Min Act: -0.1700
Data Index: 3035184 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.8187. Min Act: -0.1700
Data Index: 2074307 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.8187. Min Act: -0.1700
Data Index: 2426824 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.8187. Min Act: -0.1700
Data Index: 6936638 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.8187. Min Act: -0.1700
Data Index: 1186121 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.8187. Min Act: -0.1700
Data Index: 6011258 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.8187. Min Act: -0.1700
Data Index: 8475032 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.8187. Min Act: -0.1700
Data Index: 3756685 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.7874. Min Act: -0.1700
Data Index: 7638593 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3812. Min Range: -6.3812
Max Act: 5.7874. Min Act: -0.1700
Data Index: 5845487 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19