Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4314 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.9590. Min Act: -0.1700
Data Index: 925353 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.7090. Min Act: -0.1700
Data Index: 1025244 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.5840. Min Act: -0.1700
Data Index: 4198810 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.2715. Min Act: -0.1700
Data Index: 2228498 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.2715. Min Act: -0.1700
Data Index: 7240587 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.1465. Min Act: -0.1700
Data Index: 5510473 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.1465. Min Act: -0.1700
Data Index: 1598866 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.0840. Min Act: -0.1700
Data Index: 5718631 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.0840. Min Act: -0.1700
Data Index: 4597370 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.0840. Min Act: -0.1700
Data Index: 1470990 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.0840. Min Act: -0.1700
Data Index: 1589328 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.0215. Min Act: -0.1700
Data Index: 1299633 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.0215. Min Act: -0.1700
Data Index: 1930361 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.0215. Min Act: -0.1700
Data Index: 657167 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9590. Min Range: -9.9590
Max Act: 9.0215. Min Act: -0.1700
Data Index: 7135435 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9590. Min Range: -9.9590
Max Act: 8.9590. Min Act: -0.1700
Data Index: 7853477 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9590. Min Range: -9.9590
Max Act: 8.9590. Min Act: -0.1700
Data Index: 3080650 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9590. Min Range: -9.9590
Max Act: 8.8965. Min Act: -0.1700
Data Index: 7049373 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9590. Min Range: -9.9590
Max Act: 8.8965. Min Act: -0.1700
Data Index: 3530469 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9590. Min Range: -9.9590
Max Act: 8.8965. Min Act: -0.1700
Data Index: 4166976 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19