Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2295 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4978. Min Range: -7.4978
Max Act: 7.4978. Min Act: -0.1700
Data Index: 4015366 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4978. Min Range: -7.4978
Max Act: 7.3728. Min Act: -0.1700
Data Index: 4042297 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4978. Min Range: -7.4978
Max Act: 7.2478. Min Act: -0.1700
Data Index: 4118954 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.9978. Min Act: -0.1700
Data Index: 4124238 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.9353. Min Act: -0.1700
Data Index: 4412653 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.8728. Min Act: -0.1700
Data Index: 6784028 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.8728. Min Act: -0.1700
Data Index: 8593180 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.7478. Min Act: -0.1700
Data Index: 6672327 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.7790. Min Act: -0.1700
Data Index: 3477340 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.7478. Min Act: -0.1700
Data Index: 8585918 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.7165. Min Act: -0.1700
Data Index: 8212565 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.6853. Min Act: -0.1700
Data Index: 3944929 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.6853. Min Act: -0.1700
Data Index: 8771961 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.6853. Min Act: -0.1700
Data Index: 5658155 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.6540. Min Act: -0.1700
Data Index: 3226862 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.6853. Min Act: -0.1700
Data Index: 1484285 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.6228. Min Act: -0.1700
Data Index: 952948 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.6228. Min Act: -0.1700
Data Index: 2489427 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.6228. Min Act: -0.1700
Data Index: 8810822 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4978. Min Range: -7.4978
Max Act: 6.6228. Min Act: -0.1700
Data Index: 5688273 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19