Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.8417. Min Act: -0.1700
Data Index: 3219794 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.7479. Min Act: -0.1700
Data Index: 3219793 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.7479. Min Act: -0.1700
Data Index: 3219796 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.7167. Min Act: -0.1700
Data Index: 3219795 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.6229. Min Act: -0.1700
Data Index: 3440139 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.5292. Min Act: -0.1700
Data Index: 2488401 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.4979. Min Act: -0.1700
Data Index: 3219799 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.4979. Min Act: -0.1700
Data Index: 3219800 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.4354. Min Act: -0.1700
Data Index: 264855 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.4667. Min Act: -0.1700
Data Index: 8681425 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.4354. Min Act: -0.1700
Data Index: 3219798 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.4042. Min Act: -0.1700
Data Index: 7918777 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.4354. Min Act: -0.1700
Data Index: 4965719 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.4042. Min Act: -0.1700
Data Index: 6534904 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.3729. Min Act: -0.1700
Data Index: 2211307 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.3104. Min Act: -0.1700
Data Index: 3219791 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.3417. Min Act: -0.1700
Data Index: 1863627 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.3417. Min Act: -0.1700
Data Index: 2943159 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.3104. Min Act: -0.1700
Data Index: 7573428 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8417. Min Range: -5.8417
Max Act: 5.3104. Min Act: -0.1700
Data Index: 2344636 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19