Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8473. Min Range: -11.8473
Max Act: 11.8473. Min Act: -0.1700
Data Index: 4945004 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8473. Min Range: -11.8473
Max Act: 11.4098. Min Act: -0.1700
Data Index: 1348313 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8473. Min Range: -11.8473
Max Act: 11.2848. Min Act: -0.1700
Data Index: 7203486 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8473. Min Range: -11.8473
Max Act: 11.2223. Min Act: -0.1700
Data Index: 3041309 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8473. Min Range: -11.8473
Max Act: 11.1598. Min Act: -0.1700
Data Index: 3818631 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8473. Min Range: -11.8473
Max Act: 11.1598. Min Act: -0.1700
Data Index: 3048503 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8473. Min Range: -11.8473
Max Act: 11.1598. Min Act: -0.1700
Data Index: 4285481 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8473. Min Range: -11.8473
Max Act: 11.0973. Min Act: -0.1700
Data Index: 269880 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8473. Min Range: -11.8473
Max Act: 11.0973. Min Act: -0.1700
Data Index: 7636596 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8473. Min Range: -11.8473
Max Act: 11.0348. Min Act: -0.1700
Data Index: 5116565 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8473. Min Range: -11.8473
Max Act: 11.0348. Min Act: -0.1700
Data Index: 1260603 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8473. Min Range: -11.8473
Max Act: 11.0348. Min Act: -0.1700
Data Index: 6048593 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8473. Min Range: -11.8473
Max Act: 10.9098. Min Act: -0.1700
Data Index: 7766710 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8473. Min Range: -11.8473
Max Act: 10.9098. Min Act: -0.1700
Data Index: 3930595 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8473. Min Range: -11.8473
Max Act: 10.9098. Min Act: -0.1700
Data Index: 5080349 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8473. Min Range: -11.8473
Max Act: 10.9098. Min Act: -0.1700
Data Index: 8654407 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8473. Min Range: -11.8473
Max Act: 10.8473. Min Act: -0.1700
Data Index: 4240301 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8473. Min Range: -11.8473
Max Act: 10.8473. Min Act: -0.1700
Data Index: 8819225 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8473. Min Range: -11.8473
Max Act: 10.7848. Min Act: -0.1700
Data Index: 177604 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8473. Min Range: -11.8473
Max Act: 10.7848. Min Act: -0.1700
Data Index: 4477623 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19