Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 464 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.5425. Min Act: -0.1700
Data Index: 8432644 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.6050. Min Act: -0.1700
Data Index: 2169763 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.4800. Min Act: -0.1700
Data Index: 4085559 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.3550. Min Act: -0.1700
Data Index: 435299 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.2925. Min Act: -0.1700
Data Index: 1820592 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.2925. Min Act: -0.1700
Data Index: 5428522 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.2300. Min Act: -0.1700
Data Index: 2169760 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.1050. Min Act: -0.1700
Data Index: 7957912 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.1050. Min Act: -0.1700
Data Index: 2791330 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.1050. Min Act: -0.1700
Data Index: 435306 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.0425. Min Act: -0.1700
Data Index: 8432643 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.1050. Min Act: -0.1700
Data Index: 5318240 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.0425. Min Act: -0.1700
Data Index: 5377504 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6050. Min Range: -9.6050
Max Act: 9.0425. Min Act: -0.1700
Data Index: 2169780 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6050. Min Range: -9.6050
Max Act: 8.9800. Min Act: -0.1700
Data Index: 4085562 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6050. Min Range: -9.6050
Max Act: 8.9175. Min Act: -0.1700
Data Index: 4085558 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6050. Min Range: -9.6050
Max Act: 8.8550. Min Act: -0.1700
Data Index: 8489489 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6050. Min Range: -9.6050
Max Act: 8.7925. Min Act: -0.1700
Data Index: 8489483 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6050. Min Range: -9.6050
Max Act: 8.8550. Min Act: -0.1700
Data Index: 435298 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6050. Min Range: -9.6050
Max Act: 8.7925. Min Act: -0.1700
Data Index: 8084499 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19