Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.4473. Min Act: -0.1700
Data Index: 635177 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.4473. Min Act: -0.1700
Data Index: 8727295 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.2598. Min Act: -0.1700
Data Index: 3604273 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.2598. Min Act: -0.1700
Data Index: 6985172 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.2598. Min Act: -0.1700
Data Index: 7217245 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.1348. Min Act: -0.1700
Data Index: 6076765 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.1973. Min Act: -0.1700
Data Index: 5633306 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.1973. Min Act: -0.1700
Data Index: 4490365 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.1348. Min Act: -0.1700
Data Index: 7401696 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.1348. Min Act: -0.1700
Data Index: 6017313 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.1348. Min Act: -0.1700
Data Index: 5189615 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.0723. Min Act: -0.1700
Data Index: 8662151 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.0723. Min Act: -0.1700
Data Index: 6076766 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.0723. Min Act: -0.1700
Data Index: 2891947 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.0098. Min Act: -0.1700
Data Index: 5743127 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.0098. Min Act: -0.1700
Data Index: 3540168 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4473. Min Range: -9.4473
Max Act: 9.0098. Min Act: -0.1700
Data Index: 3641390 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4473. Min Range: -9.4473
Max Act: 8.9473. Min Act: -0.1700
Data Index: 5152993 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4473. Min Range: -9.4473
Max Act: 8.8848. Min Act: -0.1700
Data Index: 741169 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4473. Min Range: -9.4473
Max Act: 8.8848. Min Act: -0.1700
Data Index: 5600811 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19