Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4309. Min Range: -8.4309
Max Act: 8.4309. Min Act: -0.1700
Data Index: 5226759 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4309. Min Range: -8.4309
Max Act: 8.2434. Min Act: -0.1700
Data Index: 972039 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4309. Min Range: -8.4309
Max Act: 8.1809. Min Act: -0.1700
Data Index: 7299881 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4309. Min Range: -8.4309
Max Act: 8.1184. Min Act: -0.1700
Data Index: 6328223 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.9309. Min Act: -0.1700
Data Index: 6480300 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.8997. Min Act: -0.1700
Data Index: 3478030 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.8997. Min Act: -0.1700
Data Index: 8078224 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.8684. Min Act: -0.1700
Data Index: 2930333 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.8684. Min Act: -0.1700
Data Index: 7015240 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.8684. Min Act: -0.1700
Data Index: 8301725 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.8684. Min Act: -0.1700
Data Index: 999112 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.8059. Min Act: -0.1700
Data Index: 8395753 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.7747. Min Act: -0.1700
Data Index: 1550216 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.7747. Min Act: -0.1700
Data Index: 6292679 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.7434. Min Act: -0.1700
Data Index: 5787789 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.6809. Min Act: -0.1700
Data Index: 6874390 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.6184. Min Act: -0.1700
Data Index: 1024823 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.6497. Min Act: -0.1700
Data Index: 7745582 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.6184. Min Act: -0.1700
Data Index: 6509192 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4309. Min Range: -8.4309
Max Act: 7.6184. Min Act: -0.1700
Data Index: 2822339 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19