Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5990 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1131. Min Range: -7.1131
Max Act: 7.1131. Min Act: -0.1700
Data Index: 173058 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1131. Min Range: -7.1131
Max Act: 7.1131. Min Act: -0.1700
Data Index: 5001071 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.9881. Min Act: -0.1700
Data Index: 879928 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1131. Min Range: -7.1131
Max Act: 7.0193. Min Act: -0.1700
Data Index: 879926 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.9568. Min Act: -0.1700
Data Index: 7965388 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.8943. Min Act: -0.1700
Data Index: 6885573 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.8631. Min Act: -0.1700
Data Index: 7026119 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.8631. Min Act: -0.1700
Data Index: 4989995 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.8631. Min Act: -0.1700
Data Index: 737687 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.8631. Min Act: -0.1700
Data Index: 6686783 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.8318. Min Act: -0.1700
Data Index: 428001 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.8318. Min Act: -0.1700
Data Index: 1462159 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.8318. Min Act: -0.1700
Data Index: 6756033 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.7693. Min Act: -0.1700
Data Index: 1972899 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.7693. Min Act: -0.1700
Data Index: 1302008 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.7693. Min Act: -0.1700
Data Index: 1664688 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.7381. Min Act: -0.1700
Data Index: 7472614 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.7381. Min Act: -0.1700
Data Index: 4823419 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.7381. Min Act: -0.1700
Data Index: 7357621 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1131. Min Range: -7.1131
Max Act: 6.7381. Min Act: -0.1700
Data Index: 5760524 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19