Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2842 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.8078. Min Act: -0.1700
Data Index: 7854969 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.6515. Min Act: -0.1700
Data Index: 4462639 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.6203. Min Act: -0.1700
Data Index: 8094584 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.5890. Min Act: -0.1700
Data Index: 4660693 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.5265. Min Act: -0.1700
Data Index: 6803296 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.4953. Min Act: -0.1700
Data Index: 7665571 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.4953. Min Act: -0.1700
Data Index: 2502455 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.4953. Min Act: -0.1700
Data Index: 3047825 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.4640. Min Act: -0.1700
Data Index: 2010056 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.4640. Min Act: -0.1700
Data Index: 6735308 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.4328. Min Act: -0.1700
Data Index: 799419 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.4328. Min Act: -0.1700
Data Index: 6961084 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.4640. Min Act: -0.1700
Data Index: 7229971 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.4328. Min Act: -0.1700
Data Index: 799418 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.4328. Min Act: -0.1700
Data Index: 8376041 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.4015. Min Act: -0.1700
Data Index: 4660692 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.4015. Min Act: -0.1700
Data Index: 1968305 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.3703. Min Act: -0.1700
Data Index: 173189 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.3703. Min Act: -0.1700
Data Index: 3417941 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8078. Min Range: -4.8078
Max Act: 4.3703. Min Act: -0.1700
Data Index: 5924939 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19