Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1789 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7425. Min Range: -7.7425
Max Act: 7.7425. Min Act: -0.1700
Data Index: 7956059 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7425. Min Range: -7.7425
Max Act: 7.3050. Min Act: -0.1700
Data Index: 211436 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7425. Min Range: -7.7425
Max Act: 7.2738. Min Act: -0.1700
Data Index: 777359 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7425. Min Range: -7.7425
Max Act: 7.1800. Min Act: -0.1700
Data Index: 7649278 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7425. Min Range: -7.7425
Max Act: 7.1800. Min Act: -0.1700
Data Index: 8627919 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7425. Min Range: -7.7425
Max Act: 7.1488. Min Act: -0.1700
Data Index: 7735211 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7425. Min Range: -7.7425
Max Act: 7.1488. Min Act: -0.1700
Data Index: 4576973 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7425. Min Range: -7.7425
Max Act: 7.1488. Min Act: -0.1700
Data Index: 7735210 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7425. Min Range: -7.7425
Max Act: 7.1175. Min Act: -0.1700
Data Index: 7128145 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7425. Min Range: -7.7425
Max Act: 7.0238. Min Act: -0.1700
Data Index: 3823966 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7425. Min Range: -7.7425
Max Act: 6.9925. Min Act: -0.1700
Data Index: 4888233 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7425. Min Range: -7.7425
Max Act: 6.9613. Min Act: -0.1700
Data Index: 5051723 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7425. Min Range: -7.7425
Max Act: 6.9613. Min Act: -0.1700
Data Index: 7699108 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7425. Min Range: -7.7425
Max Act: 6.9613. Min Act: -0.1700
Data Index: 261555 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7425. Min Range: -7.7425
Max Act: 6.9613. Min Act: -0.1700
Data Index: 2375876 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7425. Min Range: -7.7425
Max Act: 6.8988. Min Act: -0.1700
Data Index: 7563693 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7425. Min Range: -7.7425
Max Act: 6.9300. Min Act: -0.1700
Data Index: 3145832 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7425. Min Range: -7.7425
Max Act: 6.9300. Min Act: -0.1700
Data Index: 6323598 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7425. Min Range: -7.7425
Max Act: 6.8675. Min Act: -0.1700
Data Index: 1208756 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7425. Min Range: -7.7425
Max Act: 6.8675. Min Act: -0.1700
Data Index: 8010861 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19