Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2952 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.6733. Min Act: -0.1700
Data Index: 7518479 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.5170. Min Act: -0.1700
Data Index: 2380218 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.5170. Min Act: -0.1700
Data Index: 1200808 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.3295. Min Act: -0.1700
Data Index: 7074868 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.2983. Min Act: -0.1700
Data Index: 1591428 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.2045. Min Act: -0.1700
Data Index: 1152831 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.1733. Min Act: -0.1700
Data Index: 4006765 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.1108. Min Act: -0.1700
Data Index: 1497705 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.1108. Min Act: -0.1700
Data Index: 8015843 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.0795. Min Act: -0.1700
Data Index: 4589602 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.0795. Min Act: -0.1700
Data Index: 7235676 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.0483. Min Act: -0.1700
Data Index: 7422283 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.0483. Min Act: -0.1700
Data Index: 1743609 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6733. Min Range: -7.6733
Max Act: 7.0170. Min Act: -0.1700
Data Index: 2313109 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6733. Min Range: -7.6733
Max Act: 6.9858. Min Act: -0.1700
Data Index: 5941681 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6733. Min Range: -7.6733
Max Act: 6.9858. Min Act: -0.1700
Data Index: 1200798 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6733. Min Range: -7.6733
Max Act: 6.9858. Min Act: -0.1700
Data Index: 7988147 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6733. Min Range: -7.6733
Max Act: 6.9858. Min Act: -0.1700
Data Index: 7265124 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6733. Min Range: -7.6733
Max Act: 6.9858. Min Act: -0.1700
Data Index: 625320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6733. Min Range: -7.6733
Max Act: 6.9858. Min Act: -0.1700
Data Index: 2048799 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19