Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4377 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.8100. Min Act: -0.1700
Data Index: 8192020 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.7162. Min Act: -0.1700
Data Index: 5249161 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.5912. Min Act: -0.1700
Data Index: 399940 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.5600. Min Act: -0.1700
Data Index: 2904510 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.4662. Min Act: -0.1700
Data Index: 1587785 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.4975. Min Act: -0.1700
Data Index: 3370558 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.4662. Min Act: -0.1700
Data Index: 4395443 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.4662. Min Act: -0.1696
Data Index: 1587771 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.4350. Min Act: -0.1700
Data Index: 856040 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.4350. Min Act: -0.1700
Data Index: 1587772 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.4350. Min Act: -0.1700
Data Index: 1236768 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.4350. Min Act: -0.1700
Data Index: 2864362 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.4350. Min Act: -0.1700
Data Index: 1679291 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.4037. Min Act: -0.1700
Data Index: 7899758 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.4350. Min Act: -0.1700
Data Index: 7887537 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.3725. Min Act: -0.1700
Data Index: 1403241 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.3412. Min Act: -0.1700
Data Index: 1587765 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.3100. Min Act: -0.1700
Data Index: 4657632 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.3100. Min Act: -0.1695
Data Index: 1587760 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8100. Min Range: -5.8100
Max Act: 5.3100. Min Act: -0.1700
Data Index: 8597500 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19