Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4318 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.2533. Min Act: -0.1700
Data Index: 7442235 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.2220. Min Act: -0.1700
Data Index: 3436553 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.1908. Min Act: -0.1700
Data Index: 5226971 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0970. Min Act: -0.1700
Data Index: 7244612 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.9720. Min Act: -0.1700
Data Index: 5797975 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.9408. Min Act: -0.1700
Data Index: 2148548 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.9408. Min Act: -0.1700
Data Index: 7265483 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.9408. Min Act: -0.1700
Data Index: 2898261 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.9720. Min Act: -0.1700
Data Index: 366165 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.9408. Min Act: -0.1700
Data Index: 7783844 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.8783. Min Act: -0.1700
Data Index: 7860213 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.8470. Min Act: -0.1700
Data Index: 8754664 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.8783. Min Act: -0.1700
Data Index: 5362752 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.8470. Min Act: -0.1700
Data Index: 3015261 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.7845. Min Act: -0.1700
Data Index: 3588990 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.8158. Min Act: -0.1700
Data Index: 4810226 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.8158. Min Act: -0.1700
Data Index: 3830325 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.8158. Min Act: -0.1700
Data Index: 5849151 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.8158. Min Act: -0.1700
Data Index: 4722364 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.7845. Min Act: -0.1700
Data Index: 2285919 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19