Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5281 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.9801. Min Act: -0.1700
Data Index: 6380217 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.9643. Min Act: -0.1700
Data Index: 3281407 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.9484. Min Act: -0.1700
Data Index: 652831 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.9484. Min Act: -0.1700
Data Index: 5622765 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.9326. Min Act: -0.1700
Data Index: 3569223 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.9168. Min Act: -0.1700
Data Index: 7396675 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8850. Min Act: -0.1700
Data Index: 3641067 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8692. Min Act: -0.1700
Data Index: 6037185 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8533. Min Act: -0.1700
Data Index: 6492707 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8533. Min Act: -0.1700
Data Index: 1661828 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8374. Min Act: -0.1700
Data Index: 6634976 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8374. Min Act: -0.1700
Data Index: 8037283 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8374. Min Act: -0.1700
Data Index: 5748663 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8215. Min Act: -0.1700
Data Index: 7395344 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8056. Min Act: -0.1700
Data Index: 988183 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8056. Min Act: -0.1700
Data Index: 4161699 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8056. Min Act: -0.1700
Data Index: 8486338 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8056. Min Act: -0.1700
Data Index: 7352257 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.8056. Min Act: -0.1700
Data Index: 2051258 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9801. Min Range: -2.9801
Max Act: 2.7896. Min Act: -0.1700
Data Index: 5274310 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19