Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2333 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0691. Min Range: -7.0691
Max Act: 7.0691. Min Act: -0.1700
Data Index: 413487 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.9441. Min Act: -0.1700
Data Index: 7076293 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.8816. Min Act: -0.1700
Data Index: 6726226 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.8503. Min Act: -0.1700
Data Index: 504851 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.8191. Min Act: -0.1700
Data Index: 6543089 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.7566. Min Act: -0.1700
Data Index: 4491512 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.7253. Min Act: -0.1700
Data Index: 3978693 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.6628. Min Act: -0.1700
Data Index: 6094674 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.6628. Min Act: -0.1700
Data Index: 746146 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.6628. Min Act: -0.1700
Data Index: 5431211 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.6316. Min Act: -0.1700
Data Index: 2865864 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.6003. Min Act: -0.1700
Data Index: 4903657 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.6003. Min Act: -0.1700
Data Index: 91096 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.6003. Min Act: -0.1700
Data Index: 7948788 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.5691. Min Act: -0.1700
Data Index: 7359530 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.5378. Min Act: -0.1700
Data Index: 4779155 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.5066. Min Act: -0.1700
Data Index: 2230443 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.4753. Min Act: -0.1700
Data Index: 7745715 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.5066. Min Act: -0.1700
Data Index: 5025194 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.4753. Min Act: -0.1700
Data Index: 4027102 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19