Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.9590. Min Act: -0.1700
Data Index: 834596 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.9590. Min Act: -0.1700
Data Index: 3852678 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.7715. Min Act: -0.1700
Data Index: 534255 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.7715. Min Act: -0.1700
Data Index: 7201861 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.5215. Min Act: -0.1700
Data Index: 996625 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.5215. Min Act: -0.1700
Data Index: 528502 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.3965. Min Act: -0.1700
Data Index: 691601 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.3340. Min Act: -0.1700
Data Index: 4089397 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.3340. Min Act: -0.1700
Data Index: 6065973 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.2715. Min Act: -0.1700
Data Index: 3373248 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.2715. Min Act: -0.1700
Data Index: 5516713 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.2715. Min Act: -0.1700
Data Index: 2341725 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.2090. Min Act: -0.1700
Data Index: 1073818 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.2090. Min Act: -0.1700
Data Index: 8784896 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.2090. Min Act: -0.1700
Data Index: 8499683 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.2090. Min Act: -0.1700
Data Index: 3342362 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.2090. Min Act: -0.1700
Data Index: 7025898 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.2090. Min Act: -0.1700
Data Index: 3957374 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.1465. Min Act: -0.1700
Data Index: 6140563 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9590. Min Range: -8.9590
Max Act: 8.1465. Min Act: -0.1700
Data Index: 6449024 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19