Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.8493. Min Act: -0.1700
Data Index: 7734830 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.8180. Min Act: -0.1700
Data Index: 2604836 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.6930. Min Act: -0.1700
Data Index: 5161418 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.5993. Min Act: -0.1700
Data Index: 4337296 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.4743. Min Act: -0.1700
Data Index: 7896495 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.4430. Min Act: -0.1700
Data Index: 1232206 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.4430. Min Act: -0.1700
Data Index: 7476141 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.3805. Min Act: -0.1700
Data Index: 3853668 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.3805. Min Act: -0.1700
Data Index: 2162097 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.3805. Min Act: -0.1700
Data Index: 1622957 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2868. Min Act: -0.1700
Data Index: 8112891 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2868. Min Act: -0.1700
Data Index: 7026083 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2868. Min Act: -0.1700
Data Index: 3954231 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2868. Min Act: -0.1700
Data Index: 7476136 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2868. Min Act: -0.1700
Data Index: 2711638 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2243. Min Act: -0.1700
Data Index: 2698186 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2243. Min Act: -0.1700
Data Index: 1072801 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2243. Min Act: -0.1700
Data Index: 300860 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.1930. Min Act: -0.1700
Data Index: 382334 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.1930. Min Act: -0.1700
Data Index: 7627163 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19