Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3467 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2982. Min Act: -0.1700
Data Index: 4600834 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2044. Min Act: -0.1700
Data Index: 4492003 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2044. Min Act: -0.1700
Data Index: 8632254 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2044. Min Act: -0.1700
Data Index: 3195209 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1419. Min Act: -0.1700
Data Index: 5740079 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1107. Min Act: -0.1700
Data Index: 3112570 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1107. Min Act: -0.1700
Data Index: 3345761 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0481. Min Act: -0.1700
Data Index: 7262016 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0794. Min Act: -0.1700
Data Index: 1820785 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1107. Min Act: -0.1700
Data Index: 6853447 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0794. Min Act: -0.1700
Data Index: 6210609 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0794. Min Act: -0.1700
Data Index: 3003641 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0794. Min Act: -0.1700
Data Index: 7474695 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0481. Min Act: -0.1700
Data Index: 8072551 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0481. Min Act: -0.1700
Data Index: 4774680 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0481. Min Act: -0.1700
Data Index: 4382312 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0481. Min Act: -0.1700
Data Index: 2784604 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0481. Min Act: -0.1700
Data Index: 108520 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0794. Min Act: -0.1700
Data Index: 2477535 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0481. Min Act: -0.1700
Data Index: 4090730 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19