Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.3653. Min Act: -0.1700
Data Index: 7005882 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.1778. Min Act: -0.1700
Data Index: 2475205 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.1778. Min Act: -0.1700
Data Index: 4362598 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.0528. Min Act: -0.1700
Data Index: 5313973 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.0528. Min Act: -0.1700
Data Index: 4626234 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.0215. Min Act: -0.1700
Data Index: 6910339 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3653. Min Range: -6.3653
Max Act: 6.0215. Min Act: -0.1700
Data Index: 3090130 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.9903. Min Act: -0.1700
Data Index: 8210419 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8965. Min Act: -0.1700
Data Index: 8514557 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8653. Min Act: -0.1700
Data Index: 2235639 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8653. Min Act: -0.1700
Data Index: 1880111 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8653. Min Act: -0.1700
Data Index: 515100 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8653. Min Act: -0.1700
Data Index: 3657533 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8340. Min Act: -0.1700
Data Index: 567219 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8340. Min Act: -0.1700
Data Index: 5581885 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8340. Min Act: -0.1700
Data Index: 3006852 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8340. Min Act: -0.1700
Data Index: 3373838 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8340. Min Act: -0.1700
Data Index: 7479186 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8028. Min Act: -0.1700
Data Index: 3308596 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3653. Min Range: -6.3653
Max Act: 5.8340. Min Act: -0.1700
Data Index: 4301112 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19