Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 572 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.6663. Min Act: -0.1700
Data Index: 5087912 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.4890. Min Act: -0.1700
Data Index: 3584757 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.4727. Min Act: -0.1700
Data Index: 918342 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.4727. Min Act: -0.1700
Data Index: 2538679 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.4402. Min Act: -0.1700
Data Index: 5610826 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.4402. Min Act: -0.1700
Data Index: 6451555 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.4402. Min Act: -0.1700
Data Index: 442496 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.4402. Min Act: -0.1700
Data Index: 6079426 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.4239. Min Act: -0.1700
Data Index: 1591698 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.4239. Min Act: -0.1700
Data Index: 896870 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.4239. Min Act: -0.1700
Data Index: 4524256 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.4076. Min Act: -0.1700
Data Index: 2738346 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.3913. Min Act: -0.1700
Data Index: 2753207 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.3750. Min Act: -0.1700
Data Index: 7337686 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.3913. Min Act: -0.1700
Data Index: 516754 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.3586. Min Act: -0.1700
Data Index: 3801209 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.3750. Min Act: -0.1700
Data Index: 8788155 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.3750. Min Act: -0.1700
Data Index: 3456906 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.3586. Min Act: -0.1700
Data Index: 2639347 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6663. Min Range: -2.6663
Max Act: 2.3750. Min Act: -0.1700
Data Index: 533434 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19