Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5266 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2392. Min Range: -6.2392
Max Act: 6.2392. Min Act: -0.1700
Data Index: 8001277 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2392. Min Range: -6.2392
Max Act: 6.0205. Min Act: -0.1700
Data Index: 7694233 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2392. Min Range: -6.2392
Max Act: 6.0205. Min Act: -0.1700
Data Index: 8082023 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.9267. Min Act: -0.1700
Data Index: 436188 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.8642. Min Act: -0.1700
Data Index: 4296434 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.8642. Min Act: -0.1700
Data Index: 4226386 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.8642. Min Act: -0.1700
Data Index: 4610118 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.8017. Min Act: -0.1700
Data Index: 1411279 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.8017. Min Act: -0.1700
Data Index: 7957624 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.7705. Min Act: -0.1700
Data Index: 6273010 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.7705. Min Act: -0.1700
Data Index: 7742926 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.8017. Min Act: -0.1700
Data Index: 7784709 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.7392. Min Act: -0.1700
Data Index: 569491 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.7392. Min Act: -0.1700
Data Index: 7945970 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.7392. Min Act: -0.1700
Data Index: 1888179 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.7080. Min Act: -0.1700
Data Index: 6077770 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.7392. Min Act: -0.1700
Data Index: 4319878 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.7080. Min Act: -0.1700
Data Index: 5071704 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.7080. Min Act: -0.1700
Data Index: 2498805 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2392. Min Range: -6.2392
Max Act: 5.7080. Min Act: -0.1700
Data Index: 3685069 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19