Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4535 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.5386. Min Act: -0.1700
Data Index: 3027579 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.3198. Min Act: -0.1700
Data Index: 7294596 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.3198. Min Act: -0.1700
Data Index: 1070417 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.3198. Min Act: -0.1700
Data Index: 6618186 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.2886. Min Act: -0.1700
Data Index: 3054576 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.2573. Min Act: -0.1700
Data Index: 5250858 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.1636. Min Act: -0.1700
Data Index: 2158018 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.1636. Min Act: -0.1700
Data Index: 6620857 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.1636. Min Act: -0.1700
Data Index: 1228285 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.1011. Min Act: -0.1700
Data Index: 3649794 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.0698. Min Act: -0.1700
Data Index: 1789043 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.0386. Min Act: -0.1700
Data Index: 5270522 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.0698. Min Act: -0.1700
Data Index: 2444093 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.0698. Min Act: -0.1700
Data Index: 6362896 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.0386. Min Act: -0.1700
Data Index: 4447695 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.0386. Min Act: -0.1700
Data Index: 8399323 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.0073. Min Act: -0.1700
Data Index: 977191 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.0073. Min Act: -0.1700
Data Index: 6378403 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.0073. Min Act: -0.1700
Data Index: 8137865 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5386. Min Range: -6.5386
Max Act: 6.0073. Min Act: -0.1700
Data Index: 8579584 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19