Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3300 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.3399. Min Act: -0.1700
Data Index: 6402795 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.1524. Min Act: -0.1700
Data Index: 4938048 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.2149. Min Act: -0.1700
Data Index: 6301445 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.1524. Min Act: -0.1700
Data Index: 3049241 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.1524. Min Act: -0.1700
Data Index: 5851494 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.0899. Min Act: -0.1700
Data Index: 6736603 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.0274. Min Act: -0.1700
Data Index: 8316120 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.0899. Min Act: -0.1700
Data Index: 8607710 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.0899. Min Act: -0.1700
Data Index: 2593637 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.0899. Min Act: -0.1700
Data Index: 8786294 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.0899. Min Act: -0.1700
Data Index: 6306956 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.0274. Min Act: -0.1700
Data Index: 4551457 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.0274. Min Act: -0.1700
Data Index: 224830 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.0274. Min Act: -0.1700
Data Index: 5737044 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.0274. Min Act: -0.1700
Data Index: 8754723 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3399. Min Range: -9.3399
Max Act: 9.0274. Min Act: -0.1700
Data Index: 4305277 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3399. Min Range: -9.3399
Max Act: 8.9649. Min Act: -0.1700
Data Index: 3395429 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3399. Min Range: -9.3399
Max Act: 8.9649. Min Act: -0.1700
Data Index: 3376911 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3399. Min Range: -9.3399
Max Act: 8.9649. Min Act: -0.1700
Data Index: 684226 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3399. Min Range: -9.3399
Max Act: 8.9649. Min Act: -0.1700
Data Index: 5721663 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19