Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.7134. Min Act: -0.1700
Data Index: 6878681 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.5259. Min Act: -0.1700
Data Index: 1526584 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.5259. Min Act: -0.1700
Data Index: 5332036 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.5259. Min Act: -0.1700
Data Index: 7587589 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.4634. Min Act: -0.1700
Data Index: 7504685 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.4009. Min Act: -0.1700
Data Index: 5574510 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.3696. Min Act: -0.1700
Data Index: 3469701 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.3384. Min Act: -0.1700
Data Index: 1760271 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.3384. Min Act: -0.1700
Data Index: 7493629 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.3384. Min Act: -0.1700
Data Index: 8392566 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.3384. Min Act: -0.1700
Data Index: 4959300 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.3384. Min Act: -0.1700
Data Index: 6845491 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.2759. Min Act: -0.1700
Data Index: 4252525 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.2759. Min Act: -0.1700
Data Index: 4568227 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.2759. Min Act: -0.1700
Data Index: 2180874 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.2446. Min Act: -0.1700
Data Index: 1815373 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.2759. Min Act: -0.1700
Data Index: 2141831 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.2759. Min Act: -0.1700
Data Index: 1496200 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.2446. Min Act: -0.1700
Data Index: 5190773 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7134. Min Range: -5.7134
Max Act: 5.2446. Min Act: -0.1700
Data Index: 3420201 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19