Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2671 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1634. Min Act: -0.1700
Data Index: 6660311 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1477. Min Act: -0.1700
Data Index: 4067464 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1320. Min Act: -0.1700
Data Index: 836442 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1004. Min Act: -0.1700
Data Index: 1938262 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1004. Min Act: -0.1700
Data Index: 8243773 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1004. Min Act: -0.1700
Data Index: 8488165 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1004. Min Act: -0.1700
Data Index: 2826114 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1004. Min Act: -0.1700
Data Index: 2891239 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1004. Min Act: -0.1700
Data Index: 8655604 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1004. Min Act: -0.1700
Data Index: 8371008 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1004. Min Act: -0.1700
Data Index: 7260736 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1004. Min Act: -0.1700
Data Index: 7237120 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.0847. Min Act: -0.1700
Data Index: 8569896 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.0847. Min Act: -0.1700
Data Index: 5850147 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.0689. Min Act: -0.1700
Data Index: 112782 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.0847. Min Act: -0.1700
Data Index: 2553351 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.1004. Min Act: -0.1700
Data Index: 3607597 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.0847. Min Act: -0.1700
Data Index: 6518058 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.0847. Min Act: -0.1700
Data Index: 4330612 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1634. Min Range: -3.1634
Max Act: 3.0689. Min Act: -0.1700
Data Index: 5898613 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19