Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4365 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.5114. Min Range: -17.5114
Max Act: 17.5114. Min Act: -0.1665
Data Index: 8013116 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.5114. Min Range: -17.5114
Max Act: 17.1364. Min Act: -0.1695
Data Index: 4066239 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.7614. Min Act: -0.1699
Data Index: 1466527 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.7614. Min Act: -0.1700
Data Index: 7471536 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.7614. Min Act: -0.1692
Data Index: 4569340 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.4489. Min Act: -0.1700
Data Index: 362089 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.4489. Min Act: -0.1700
Data Index: 7742011 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.3239. Min Act: -0.1700
Data Index: 1210983 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.3864. Min Act: -0.1695
Data Index: 2565061 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.3239. Min Act: -0.1700
Data Index: 8374965 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.1989. Min Act: -0.1700
Data Index: 1251423 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.1989. Min Act: -0.1700
Data Index: 8726776 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.1364. Min Act: -0.1700
Data Index: 7688336 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.1364. Min Act: -0.1684
Data Index: 1212792 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.1364. Min Act: -0.1700
Data Index: 8098298 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.1364. Min Act: -0.1700
Data Index: 1639533 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.0114. Min Act: -0.1700
Data Index: 5191356 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.0739. Min Act: -0.1699
Data Index: 7287303 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.0114. Min Act: -0.1700
Data Index: 4048699 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.5114. Min Range: -17.5114
Max Act: 16.0739. Min Act: -0.1700
Data Index: 2703026 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19