Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.7508. Min Act: -0.1700
Data Index: 2932984 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.7196. Min Act: -0.1700
Data Index: 3532442 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.6883. Min Act: -0.1700
Data Index: 443860 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.6571. Min Act: -0.1700
Data Index: 6617435 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.5946. Min Act: -0.1700
Data Index: 7356663 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.5321. Min Act: -0.1700
Data Index: 1607875 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.5321. Min Act: -0.1700
Data Index: 4091555 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.5321. Min Act: -0.1700
Data Index: 4098267 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.5008. Min Act: -0.1700
Data Index: 8289456 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.4696. Min Act: -0.1700
Data Index: 6246686 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.4383. Min Act: -0.1700
Data Index: 8415843 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.4696. Min Act: -0.1700
Data Index: 974626 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.4696. Min Act: -0.1700
Data Index: 4438936 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.4696. Min Act: -0.1700
Data Index: 4205354 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.4383. Min Act: -0.1700
Data Index: 8711856 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.4383. Min Act: -0.1700
Data Index: 4991215 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.4071. Min Act: -0.1700
Data Index: 8069472 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.4071. Min Act: -0.1700
Data Index: 391237 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.4071. Min Act: -0.1700
Data Index: 6715961 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7508. Min Range: -5.7508
Max Act: 5.3758. Min Act: -0.1700
Data Index: 7257378 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19