Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2829 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4199. Min Range: -8.4199
Max Act: 8.4199. Min Act: -0.1700
Data Index: 7093641 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4199. Min Range: -8.4199
Max Act: 8.0136. Min Act: -0.1700
Data Index: 8669746 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4199. Min Range: -8.4199
Max Act: 8.0136. Min Act: -0.1700
Data Index: 4191716 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.9824. Min Act: -0.1700
Data Index: 4967258 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.9511. Min Act: -0.1700
Data Index: 3111765 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.8886. Min Act: -0.1700
Data Index: 5218824 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.8574. Min Act: -0.1700
Data Index: 508031 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.8574. Min Act: -0.1700
Data Index: 1313376 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.8261. Min Act: -0.1700
Data Index: 3105112 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.7949. Min Act: -0.1700
Data Index: 4495987 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.7949. Min Act: -0.1700
Data Index: 5646624 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.7636. Min Act: -0.1700
Data Index: 4075529 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.7324. Min Act: -0.1700
Data Index: 1985323 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.7324. Min Act: -0.1700
Data Index: 1238989 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.7011. Min Act: -0.1700
Data Index: 3804011 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.7011. Min Act: -0.1700
Data Index: 2351185 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.7011. Min Act: -0.1700
Data Index: 4407760 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.6699. Min Act: -0.1700
Data Index: 8569729 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.6699. Min Act: -0.1700
Data Index: 1148597 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4199. Min Range: -8.4199
Max Act: 7.6699. Min Act: -0.1700
Data Index: 2430576 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19