Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4106 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0558. Min Range: -8.0558
Max Act: 8.0558. Min Act: -0.1700
Data Index: 2938026 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.5871. Min Act: -0.1700
Data Index: 6204510 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.4308. Min Act: -0.1700
Data Index: 8335021 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.3371. Min Act: -0.1700
Data Index: 8293566 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.2746. Min Act: -0.1700
Data Index: 1725489 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.2433. Min Act: -0.1700
Data Index: 2512191 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.2433. Min Act: -0.1700
Data Index: 5361242 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.2746. Min Act: -0.1700
Data Index: 3168434 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.2121. Min Act: -0.1700
Data Index: 5361222 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.1496. Min Act: -0.1700
Data Index: 5361237 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.1496. Min Act: -0.1700
Data Index: 4142373 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.1183. Min Act: -0.1700
Data Index: 4569717 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.0871. Min Act: -0.1700
Data Index: 5361239 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.0871. Min Act: -0.1700
Data Index: 5361218 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.0558. Min Act: -0.1700
Data Index: 2825308 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0558. Min Range: -8.0558
Max Act: 7.0246. Min Act: -0.1700
Data Index: 6423323 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0558. Min Range: -8.0558
Max Act: 6.9621. Min Act: -0.1700
Data Index: 1537670 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0558. Min Range: -8.0558
Max Act: 6.9933. Min Act: -0.1700
Data Index: 5361231 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0558. Min Range: -8.0558
Max Act: 6.9933. Min Act: -0.1700
Data Index: 6357192 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0558. Min Range: -8.0558
Max Act: 6.9621. Min Act: -0.1700
Data Index: 5361246 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19