Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4000 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3550. Min Range: -6.3550
Max Act: 6.3550. Min Act: -0.1700
Data Index: 5352972 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3550. Min Range: -6.3550
Max Act: 6.1675. Min Act: -0.1700
Data Index: 8247009 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9800. Min Act: -0.1700
Data Index: 667793 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9800. Min Act: -0.1700
Data Index: 8301584 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9800. Min Act: -0.1700
Data Index: 3731722 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9488. Min Act: -0.1700
Data Index: 8102469 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9488. Min Act: -0.1700
Data Index: 4794766 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9175. Min Act: -0.1700
Data Index: 4760570 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.9175. Min Act: -0.1700
Data Index: 720822 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.8863. Min Act: -0.1700
Data Index: 3215856 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.8550. Min Act: -0.1700
Data Index: 3011864 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.8550. Min Act: -0.1700
Data Index: 5672834 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.8238. Min Act: -0.1700
Data Index: 1997491 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.7925. Min Act: -0.1700
Data Index: 7458835 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.8238. Min Act: -0.1700
Data Index: 7311612 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.7925. Min Act: -0.1700
Data Index: 7371885 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.8238. Min Act: -0.1700
Data Index: 3200793 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.7613. Min Act: -0.1700
Data Index: 1743749 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.7925. Min Act: -0.1700
Data Index: 6053740 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3550. Min Range: -6.3550
Max Act: 5.7925. Min Act: -0.1700
Data Index: 6638780 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19