Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2260 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9597. Min Range: -8.9597
Max Act: 8.9597. Min Act: -0.1700
Data Index: 3987399 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9597. Min Range: -8.9597
Max Act: 8.6472. Min Act: -0.1700
Data Index: 4285553 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9597. Min Range: -8.9597
Max Act: 8.3347. Min Act: -0.1700
Data Index: 6391679 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9597. Min Range: -8.9597
Max Act: 8.3347. Min Act: -0.1700
Data Index: 2552010 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9597. Min Range: -8.9597
Max Act: 8.0535. Min Act: -0.1700
Data Index: 948541 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9597. Min Range: -8.9597
Max Act: 8.0222. Min Act: -0.1700
Data Index: 261449 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.9285. Min Act: -0.1700
Data Index: 8156798 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.8660. Min Act: -0.1700
Data Index: 7266444 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.8660. Min Act: -0.1700
Data Index: 3770322 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.8972. Min Act: -0.1700
Data Index: 4563178 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.8347. Min Act: -0.1700
Data Index: 2783555 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.7722. Min Act: -0.1700
Data Index: 154041 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.7410. Min Act: -0.1700
Data Index: 71726 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.7410. Min Act: -0.1700
Data Index: 448446 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.6785. Min Act: -0.1700
Data Index: 3292479 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.6785. Min Act: -0.1700
Data Index: 6398978 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.6785. Min Act: -0.1700
Data Index: 4917704 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.6472. Min Act: -0.1700
Data Index: 7377926 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.6472. Min Act: -0.1700
Data Index: 7933747 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9597. Min Range: -8.9597
Max Act: 7.6472. Min Act: -0.1700
Data Index: 7166737 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19