Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.9629. Min Act: -0.1700
Data Index: 83538 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.9629. Min Act: -0.1700
Data Index: 7210548 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.7754. Min Act: -0.1700
Data Index: 3831195 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.7442. Min Act: -0.1700
Data Index: 3954780 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.7129. Min Act: -0.1700
Data Index: 1741088 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.6817. Min Act: -0.1700
Data Index: 3137952 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.5254. Min Act: -0.1700
Data Index: 8743687 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.5254. Min Act: -0.1700
Data Index: 5623197 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.5254. Min Act: -0.1700
Data Index: 8349041 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.4942. Min Act: -0.1700
Data Index: 1488607 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.4629. Min Act: -0.1700
Data Index: 4880226 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.4629. Min Act: -0.1700
Data Index: 2538813 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.4317. Min Act: -0.1700
Data Index: 6255657 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.4004. Min Act: -0.1700
Data Index: 7862973 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.4004. Min Act: -0.1700
Data Index: 5128857 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.3692. Min Act: -0.1700
Data Index: 7725829 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.4004. Min Act: -0.1700
Data Index: 6829744 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.3692. Min Act: -0.1700
Data Index: 7316406 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.3692. Min Act: -0.1700
Data Index: 2976322 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9629. Min Range: -7.9629
Max Act: 7.3692. Min Act: -0.1700
Data Index: 880935 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19