Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 123 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2396. Min Range: -8.2396
Max Act: 8.2396. Min Act: -0.1700
Data Index: 7723229 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.9896. Min Act: -0.1700
Data Index: 6048973 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.9271. Min Act: -0.1700
Data Index: 6754362 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.9896. Min Act: -0.1700
Data Index: 268679 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.8646. Min Act: -0.1700
Data Index: 1662238 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.8646. Min Act: -0.1700
Data Index: 6738113 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.8021. Min Act: -0.1700
Data Index: 1987528 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.7396. Min Act: -0.1700
Data Index: 8106799 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.7396. Min Act: -0.1700
Data Index: 6760987 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.6771. Min Act: -0.1700
Data Index: 1233136 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.6771. Min Act: -0.1700
Data Index: 718829 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.6771. Min Act: -0.1700
Data Index: 6343990 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.6459. Min Act: -0.1700
Data Index: 8709160 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.5834. Min Act: -0.1700
Data Index: 4597459 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.6146. Min Act: -0.1700
Data Index: 3049120 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.5834. Min Act: -0.1700
Data Index: 1952241 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.5834. Min Act: -0.1700
Data Index: 8457957 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.5521. Min Act: -0.1700
Data Index: 6684635 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.5209. Min Act: -0.1700
Data Index: 998661 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2396. Min Range: -8.2396
Max Act: 7.4896. Min Act: -0.1700
Data Index: 3247535 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19