Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1999 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.4511. Min Act: -0.1700
Data Index: 1056085 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.3574. Min Act: -0.1700
Data Index: 6999226 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.2949. Min Act: -0.1700
Data Index: 1117976 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.2949. Min Act: -0.1700
Data Index: 6638619 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.2636. Min Act: -0.1700
Data Index: 4125137 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.2636. Min Act: -0.1700
Data Index: 5493052 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.2636. Min Act: -0.1700
Data Index: 5472681 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.2324. Min Act: -0.1700
Data Index: 284911 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.2011. Min Act: -0.1700
Data Index: 6298208 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.2011. Min Act: -0.1700
Data Index: 4177363 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.1699. Min Act: -0.1700
Data Index: 8365083 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.1699. Min Act: -0.1700
Data Index: 407984 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.1699. Min Act: -0.1700
Data Index: 7953041 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.1699. Min Act: -0.1700
Data Index: 8386848 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.1699. Min Act: -0.1700
Data Index: 8427404 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.1699. Min Act: -0.1700
Data Index: 7135257 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.1699. Min Act: -0.1700
Data Index: 6166117 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.1699. Min Act: -0.1700
Data Index: 329398 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.1699. Min Act: -0.1700
Data Index: 2394681 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4511. Min Range: -4.4511
Max Act: 4.1386. Min Act: -0.1700
Data Index: 5985204 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19