Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.3653. Min Act: -0.1700
Data Index: 3702346 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.3340. Min Act: -0.1700
Data Index: 4865044 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.3028. Min Act: -0.1700
Data Index: 182587 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.3028. Min Act: -0.1700
Data Index: 7280241 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.2090. Min Act: -0.1700
Data Index: 5088002 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.2403. Min Act: -0.1700
Data Index: 7608017 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.2403. Min Act: -0.1700
Data Index: 4786004 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.2090. Min Act: -0.1700
Data Index: 6494816 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.1778. Min Act: -0.1700
Data Index: 3423402 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.1778. Min Act: -0.1700
Data Index: 387606 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.1465. Min Act: -0.1700
Data Index: 5625704 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.1153. Min Act: -0.1700
Data Index: 114353 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.1153. Min Act: -0.1700
Data Index: 7782452 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.1153. Min Act: -0.1700
Data Index: 7886369 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.1153. Min Act: -0.1700
Data Index: 1706102 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.1153. Min Act: -0.1700
Data Index: 2265048 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.1153. Min Act: -0.1700
Data Index: 5137355 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.0840. Min Act: -0.1700
Data Index: 5498649 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.0840. Min Act: -0.1700
Data Index: 6956984 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3653. Min Range: -5.3653
Max Act: 5.0840. Min Act: -0.1700
Data Index: 6384107 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19