Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2697 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.3570. Min Act: -0.1700
Data Index: 5749184 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.2320. Min Act: -0.1700
Data Index: 8464068 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.2632. Min Act: -0.1700
Data Index: 1050959 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.2320. Min Act: -0.1700
Data Index: 824301 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.2320. Min Act: -0.1700
Data Index: 532551 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.2007. Min Act: -0.1700
Data Index: 3687010 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.1382. Min Act: -0.1700
Data Index: 7935820 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.1382. Min Act: -0.1700
Data Index: 5765954 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.0757. Min Act: -0.1700
Data Index: 7380954 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.0757. Min Act: -0.1700
Data Index: 924729 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.0757. Min Act: -0.1700
Data Index: 749008 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.0757. Min Act: -0.1700
Data Index: 90597 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.0444. Min Act: -0.1700
Data Index: 5639805 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.0444. Min Act: -0.1700
Data Index: 3150697 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.0132. Min Act: -0.1700
Data Index: 1577716 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.0444. Min Act: -0.1700
Data Index: 2647998 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.0444. Min Act: -0.1700
Data Index: 8002382 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3570. Min Range: -4.3570
Max Act: 4.0132. Min Act: -0.1700
Data Index: 8503946 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3570. Min Range: -4.3570
Max Act: 3.9506. Min Act: -0.1700
Data Index: 4981981 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3570. Min Range: -4.3570
Max Act: 3.9819. Min Act: -0.1700
Data Index: 6841589 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19