Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4017. Min Range: -8.4017
Max Act: 8.4017. Min Act: -0.1700
Data Index: 5906724 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4017. Min Range: -8.4017
Max Act: 8.0892. Min Act: -0.1700
Data Index: 7357978 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4017. Min Range: -8.4017
Max Act: 8.0267. Min Act: -0.1700
Data Index: 8147982 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4017. Min Range: -8.4017
Max Act: 8.0892. Min Act: -0.1700
Data Index: 4826934 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.9642. Min Act: -0.1700
Data Index: 6501660 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.9642. Min Act: -0.1700
Data Index: 5906725 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.9017. Min Act: -0.1700
Data Index: 482054 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.8392. Min Act: -0.1700
Data Index: 6195394 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.8080. Min Act: -0.1700
Data Index: 5561932 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.7767. Min Act: -0.1700
Data Index: 6009747 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.7455. Min Act: -0.1700
Data Index: 3853517 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.7142. Min Act: -0.1700
Data Index: 5750562 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.7142. Min Act: -0.1700
Data Index: 4287258 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.7142. Min Act: -0.1700
Data Index: 5345276 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.6517. Min Act: -0.1700
Data Index: 5750561 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.6205. Min Act: -0.1700
Data Index: 5478793 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.6517. Min Act: -0.1700
Data Index: 5468348 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.6517. Min Act: -0.1700
Data Index: 3844539 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.5892. Min Act: -0.1700
Data Index: 7638435 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4017. Min Range: -8.4017
Max Act: 7.5892. Min Act: -0.1700
Data Index: 5529216 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19