Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5448 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3724. Min Range: -9.3724
Max Act: 9.3724. Min Act: -0.1700
Data Index: 2464035 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3724. Min Range: -9.3724
Max Act: 9.2474. Min Act: -0.1700
Data Index: 6433909 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3724. Min Range: -9.3724
Max Act: 9.2474. Min Act: -0.1700
Data Index: 5038762 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.9974. Min Act: -0.1700
Data Index: 6377131 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.9349. Min Act: -0.1700
Data Index: 6617000 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.9974. Min Act: -0.1700
Data Index: 2020002 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.9349. Min Act: -0.1700
Data Index: 4582955 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.9349. Min Act: -0.1700
Data Index: 8262929 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.8724. Min Act: -0.1700
Data Index: 674426 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.8724. Min Act: -0.1700
Data Index: 8521947 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.7474. Min Act: -0.1700
Data Index: 1305482 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.7474. Min Act: -0.1700
Data Index: 5530424 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.7474. Min Act: -0.1700
Data Index: 6517843 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.6849. Min Act: -0.1700
Data Index: 878337 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.6224. Min Act: -0.1700
Data Index: 6774484 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.6224. Min Act: -0.1700
Data Index: 8630904 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.6849. Min Act: -0.1700
Data Index: 1057774 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.5599. Min Act: -0.1700
Data Index: 5149374 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.6224. Min Act: -0.1700
Data Index: 1729796 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3724. Min Range: -9.3724
Max Act: 8.6224. Min Act: -0.1700
Data Index: 5585551 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19