Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4318 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2698. Min Range: -5.2698
Max Act: 5.2698. Min Act: -0.1700
Data Index: 5960596 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2698. Min Range: -5.2698
Max Act: 5.1135. Min Act: -0.1700
Data Index: 5439969 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2698. Min Range: -5.2698
Max Act: 5.0510. Min Act: -0.1700
Data Index: 2065798 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2698. Min Range: -5.2698
Max Act: 5.0510. Min Act: -0.1700
Data Index: 8766124 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2698. Min Range: -5.2698
Max Act: 5.0198. Min Act: -0.1700
Data Index: 3558744 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.9885. Min Act: -0.1700
Data Index: 8622827 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.9885. Min Act: -0.1700
Data Index: 6440195 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.9260. Min Act: -0.1700
Data Index: 5942087 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8948. Min Act: -0.1700
Data Index: 4998777 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8323. Min Act: -0.1700
Data Index: 6345991 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8635. Min Act: -0.1700
Data Index: 5277732 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8635. Min Act: -0.1700
Data Index: 8271070 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8323. Min Act: -0.1700
Data Index: 6184592 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8635. Min Act: -0.1700
Data Index: 2088941 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8323. Min Act: -0.1700
Data Index: 6981888 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8323. Min Act: -0.1700
Data Index: 1205515 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.7698. Min Act: -0.1700
Data Index: 2671612 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8010. Min Act: -0.1700
Data Index: 6404012 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8010. Min Act: -0.1700
Data Index: 573935 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8010. Min Act: -0.1700
Data Index: 1850799 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19