Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4926 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.9805. Min Act: -0.1700
Data Index: 2998271 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.9492. Min Act: -0.1700
Data Index: 6918254 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.9180. Min Act: -0.1700
Data Index: 8388862 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.9180. Min Act: -0.1700
Data Index: 4321009 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.9180. Min Act: -0.1700
Data Index: 810207 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.9180. Min Act: -0.1700
Data Index: 3377374 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.8555. Min Act: -0.1700
Data Index: 4309047 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.8242. Min Act: -0.1700
Data Index: 6450605 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.7930. Min Act: -0.1700
Data Index: 1309416 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.7930. Min Act: -0.1700
Data Index: 802379 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.7617. Min Act: -0.1700
Data Index: 6603253 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.7617. Min Act: -0.1700
Data Index: 832795 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.7930. Min Act: -0.1700
Data Index: 4181455 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.6992. Min Act: -0.1700
Data Index: 1580369 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.6992. Min Act: -0.1700
Data Index: 3939671 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.6992. Min Act: -0.1700
Data Index: 1385935 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.6992. Min Act: -0.1700
Data Index: 5692065 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.6992. Min Act: -0.1700
Data Index: 3670276 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.6680. Min Act: -0.1700
Data Index: 3869425 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9805. Min Range: -6.9805
Max Act: 6.6680. Min Act: -0.1700
Data Index: 4513060 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19