Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2622 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0434. Min Range: -10.0434
Max Act: 10.0434. Min Act: -0.1700
Data Index: 5742339 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.9184. Min Act: -0.1700
Data Index: 3953219 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.7934. Min Act: -0.1700
Data Index: 3738144 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.6684. Min Act: -0.1700
Data Index: 3418231 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.6684. Min Act: -0.1700
Data Index: 7131447 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.6684. Min Act: -0.1700
Data Index: 4133255 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.6059. Min Act: -0.1700
Data Index: 8248657 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.6059. Min Act: -0.1700
Data Index: 7221486 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.6059. Min Act: -0.1700
Data Index: 6172844 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.6059. Min Act: -0.1700
Data Index: 6794078 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.5434. Min Act: -0.1700
Data Index: 3494401 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.4809. Min Act: -0.1700
Data Index: 4819853 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.4809. Min Act: -0.1700
Data Index: 4092935 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.4184. Min Act: -0.1700
Data Index: 2760372 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.4184. Min Act: -0.1700
Data Index: 6549829 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.4184. Min Act: -0.1700
Data Index: 952689 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.4184. Min Act: -0.1700
Data Index: 7092872 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.4184. Min Act: -0.1700
Data Index: 7463189 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.3559. Min Act: -0.1700
Data Index: 8200227 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0434. Min Range: -10.0434
Max Act: 9.3559. Min Act: -0.1700
Data Index: 7483929 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19