Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4610 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.9706. Min Act: -0.1700
Data Index: 5364379 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.9706. Min Act: -0.1700
Data Index: 5416559 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.9393. Min Act: -0.1700
Data Index: 8594980 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.9393. Min Act: -0.1700
Data Index: 7704481 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.9706. Min Act: -0.1700
Data Index: 3419484 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.9393. Min Act: -0.1700
Data Index: 1837695 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8768. Min Act: -0.1700
Data Index: 3481152 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8768. Min Act: -0.1700
Data Index: 5416558 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8768. Min Act: -0.1700
Data Index: 938227 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8455. Min Act: -0.1700
Data Index: 2065950 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8455. Min Act: -0.1700
Data Index: 8761947 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8455. Min Act: -0.1700
Data Index: 8005634 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8768. Min Act: -0.1700
Data Index: 4626539 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8455. Min Act: -0.1700
Data Index: 447497 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8455. Min Act: -0.1700
Data Index: 8594979 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8455. Min Act: -0.1700
Data Index: 7704480 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8143. Min Act: -0.1700
Data Index: 8646376 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8143. Min Act: -0.1700
Data Index: 905028 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.7830. Min Act: -0.1700
Data Index: 1707621 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9706. Min Range: -3.9706
Max Act: 3.8143. Min Act: -0.1700
Data Index: 447498 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19