Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.9561. Min Act: -0.1700
Data Index: 4698992 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.8935. Min Act: -0.1700
Data Index: 2393087 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.7685. Min Act: -0.1700
Data Index: 2044516 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.7685. Min Act: -0.1700
Data Index: 821491 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.7528. Min Act: -0.1700
Data Index: 3879304 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.7215. Min Act: -0.1700
Data Index: 2129460 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.7215. Min Act: -0.1700
Data Index: 3861078 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.7215. Min Act: -0.1700
Data Index: 7826762 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.7059. Min Act: -0.1700
Data Index: 4167621 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.6746. Min Act: -0.1700
Data Index: 4600370 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.6746. Min Act: -0.1700
Data Index: 7278259 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.6590. Min Act: -0.1700
Data Index: 5351254 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.6590. Min Act: -0.1700
Data Index: 3716841 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.6590. Min Act: -0.1700
Data Index: 5401514 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.6433. Min Act: -0.1700
Data Index: 4860700 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.6433. Min Act: -0.1700
Data Index: 4205166 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.6277. Min Act: -0.1700
Data Index: 4243789 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.6433. Min Act: -0.1700
Data Index: 118360 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.6120. Min Act: -0.1700
Data Index: 5372072 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9561. Min Range: -3.9561
Max Act: 3.6277. Min Act: -0.1700
Data Index: 6102999 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19