Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4161 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3509. Min Range: -7.3509
Max Act: 7.3509. Min Act: -0.1700
Data Index: 4966901 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3509. Min Range: -7.3509
Max Act: 7.1946. Min Act: -0.1700
Data Index: 8080908 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3509. Min Range: -7.3509
Max Act: 7.1009. Min Act: -0.1700
Data Index: 2473231 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3509. Min Range: -7.3509
Max Act: 7.0071. Min Act: -0.1700
Data Index: 3731947 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.9759. Min Act: -0.1700
Data Index: 8483726 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.9759. Min Act: -0.1700
Data Index: 7338187 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.9759. Min Act: -0.1700
Data Index: 3234417 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.9759. Min Act: -0.1700
Data Index: 401653 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.9446. Min Act: -0.1700
Data Index: 300089 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.9134. Min Act: -0.1700
Data Index: 7672476 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.8821. Min Act: -0.1700
Data Index: 2056226 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.8509. Min Act: -0.1700
Data Index: 7698801 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.8196. Min Act: -0.1700
Data Index: 775581 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.7884. Min Act: -0.1700
Data Index: 2443100 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.8196. Min Act: -0.1700
Data Index: 238108 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.7571. Min Act: -0.1700
Data Index: 2807769 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.7571. Min Act: -0.1700
Data Index: 4040574 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.7571. Min Act: -0.1700
Data Index: 5940345 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.6946. Min Act: -0.1700
Data Index: 4907473 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3509. Min Range: -7.3509
Max Act: 6.7259. Min Act: -0.1700
Data Index: 5801280 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19