Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6114. Min Range: -8.6114
Max Act: 8.6114. Min Act: -0.1700
Data Index: 6612577 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6114. Min Range: -8.6114
Max Act: 8.3614. Min Act: -0.1700
Data Index: 7288838 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6114. Min Range: -8.6114
Max Act: 8.1739. Min Act: -0.1700
Data Index: 1436894 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6114. Min Range: -8.6114
Max Act: 8.0489. Min Act: -0.1700
Data Index: 3924857 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6114. Min Range: -8.6114
Max Act: 8.0489. Min Act: -0.1700
Data Index: 141574 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.9864. Min Act: -0.1700
Data Index: 5180544 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.9864. Min Act: -0.1700
Data Index: 3218293 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.9864. Min Act: -0.1700
Data Index: 2138929 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.9864. Min Act: -0.1700
Data Index: 866661 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.9239. Min Act: -0.1700
Data Index: 7274465 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.9239. Min Act: -0.1700
Data Index: 2986755 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.9239. Min Act: -0.1700
Data Index: 1158071 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.8614. Min Act: -0.1700
Data Index: 6280656 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.8614. Min Act: -0.1700
Data Index: 2794896 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.8302. Min Act: -0.1700
Data Index: 8119309 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.8614. Min Act: -0.1700
Data Index: 680017 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.7677. Min Act: -0.1700
Data Index: 17865 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.7989. Min Act: -0.1700
Data Index: 6249744 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.7677. Min Act: -0.1700
Data Index: 3160410 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6114. Min Range: -8.6114
Max Act: 7.7677. Min Act: -0.1700
Data Index: 3711373 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19