Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0847. Min Range: -4.0847
Max Act: 4.0847. Min Act: -0.1700
Data Index: 6156716 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.9597. Min Act: -0.1700
Data Index: 8399518 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8971. Min Act: -0.1700
Data Index: 1287707 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8971. Min Act: -0.1700
Data Index: 3264210 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8659. Min Act: -0.1700
Data Index: 651777 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8659. Min Act: -0.1700
Data Index: 4937195 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8033. Min Act: -0.1700
Data Index: 7890392 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.8346. Min Act: -0.1700
Data Index: 8747478 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.7408. Min Act: -0.1700
Data Index: 5144735 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.7408. Min Act: -0.1700
Data Index: 7104293 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.7408. Min Act: -0.1700
Data Index: 5051645 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.7408. Min Act: -0.1700
Data Index: 84669 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.6938. Min Act: -0.1700
Data Index: 5380298 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.7095. Min Act: -0.1700
Data Index: 4841607 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.7095. Min Act: -0.1700
Data Index: 3705383 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.6938. Min Act: -0.1700
Data Index: 3205655 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.6938. Min Act: -0.1700
Data Index: 4566036 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.6938. Min Act: -0.1700
Data Index: 7060549 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.6938. Min Act: -0.1700
Data Index: 599946 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0847. Min Range: -4.0847
Max Act: 3.6938. Min Act: -0.1700
Data Index: 3003815 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19