Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4825 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.9885. Min Act: -0.1700
Data Index: 5706349 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.8322. Min Act: -0.1700
Data Index: 8157929 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.7385. Min Act: -0.1700
Data Index: 3519272 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.7072. Min Act: -0.1700
Data Index: 4260726 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.7072. Min Act: -0.1700
Data Index: 311983 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.6760. Min Act: -0.1700
Data Index: 8266594 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.7072. Min Act: -0.1700
Data Index: 5644037 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.6760. Min Act: -0.1700
Data Index: 1394463 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.6447. Min Act: -0.1700
Data Index: 840631 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.6135. Min Act: -0.1700
Data Index: 4147811 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.6135. Min Act: -0.1700
Data Index: 908433 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.5822. Min Act: -0.1700
Data Index: 1769242 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.5197. Min Act: -0.1700
Data Index: 6053576 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.4885. Min Act: -0.1700
Data Index: 1633776 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.4885. Min Act: -0.1700
Data Index: 3925470 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.4572. Min Act: -0.1700
Data Index: 11484 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.4572. Min Act: -0.1700
Data Index: 5286747 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.4572. Min Act: -0.1700
Data Index: 6533217 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.4572. Min Act: -0.1700
Data Index: 1768468 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9885. Min Range: -6.9885
Max Act: 6.4885. Min Act: -0.1700
Data Index: 1306282 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19