Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2725 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0334. Min Range: -10.0334
Max Act: 10.0334. Min Act: -0.1700
Data Index: 2260899 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.9084. Min Act: -0.1700
Data Index: 6398086 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.8459. Min Act: -0.1700
Data Index: 1686660 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.7834. Min Act: -0.1700
Data Index: 7299726 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.7834. Min Act: -0.1700
Data Index: 1424387 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.7209. Min Act: -0.1700
Data Index: 1294844 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.6584. Min Act: -0.1700
Data Index: 7700083 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.7209. Min Act: -0.1700
Data Index: 21309 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.7209. Min Act: -0.1700
Data Index: 2196399 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.6584. Min Act: -0.1700
Data Index: 2652082 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.7209. Min Act: -0.1700
Data Index: 3481198 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.6584. Min Act: -0.1700
Data Index: 8636792 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.6584. Min Act: -0.1700
Data Index: 7507415 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.7209. Min Act: -0.1700
Data Index: 7743640 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.6584. Min Act: -0.1700
Data Index: 4428430 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.6584. Min Act: -0.1700
Data Index: 4868178 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.6584. Min Act: -0.1700
Data Index: 2052261 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.5959. Min Act: -0.1700
Data Index: 4799125 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.5959. Min Act: -0.1700
Data Index: 2430210 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0334. Min Range: -10.0334
Max Act: 9.5959. Min Act: -0.1700
Data Index: 1230362 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19