Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3144 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3477. Min Range: -7.3477
Max Act: 7.3477. Min Act: -0.1700
Data Index: 3819797 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3477. Min Range: -7.3477
Max Act: 7.3164. Min Act: -0.1700
Data Index: 309038 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3477. Min Range: -7.3477
Max Act: 7.1914. Min Act: -0.1700
Data Index: 5563384 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3477. Min Range: -7.3477
Max Act: 7.0977. Min Act: -0.1700
Data Index: 4072296 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3477. Min Range: -7.3477
Max Act: 7.0352. Min Act: -0.1700
Data Index: 7293719 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3477. Min Range: -7.3477
Max Act: 7.0352. Min Act: -0.1700
Data Index: 4928154 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.9727. Min Act: -0.1700
Data Index: 6585497 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.9727. Min Act: -0.1700
Data Index: 5609880 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.9414. Min Act: -0.1700
Data Index: 6223882 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.9102. Min Act: -0.1700
Data Index: 4046272 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.8789. Min Act: -0.1700
Data Index: 1608544 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.9102. Min Act: -0.1700
Data Index: 2661684 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.8789. Min Act: -0.1700
Data Index: 3951484 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.8789. Min Act: -0.1700
Data Index: 2469875 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.8789. Min Act: -0.1700
Data Index: 1018921 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.8477. Min Act: -0.1700
Data Index: 5641538 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.8164. Min Act: -0.1700
Data Index: 542158 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.8477. Min Act: -0.1700
Data Index: 7155864 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.8164. Min Act: -0.1700
Data Index: 6468563 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3477. Min Range: -7.3477
Max Act: 6.8164. Min Act: -0.1700
Data Index: 7393967 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19