Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5362 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6717. Min Range: -8.6717
Max Act: 8.6717. Min Act: -0.1700
Data Index: 8119295 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6717. Min Range: -8.6717
Max Act: 8.4842. Min Act: -0.1700
Data Index: 1204065 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6717. Min Range: -8.6717
Max Act: 8.4217. Min Act: -0.1700
Data Index: 4717457 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6717. Min Range: -8.6717
Max Act: 8.3592. Min Act: -0.1700
Data Index: 814497 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6717. Min Range: -8.6717
Max Act: 8.2967. Min Act: -0.1700
Data Index: 1082958 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6717. Min Range: -8.6717
Max Act: 8.1717. Min Act: -0.1700
Data Index: 7623214 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6717. Min Range: -8.6717
Max Act: 8.0467. Min Act: -0.1700
Data Index: 3354465 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6717. Min Range: -8.6717
Max Act: 8.0467. Min Act: -0.1700
Data Index: 900012 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6717. Min Range: -8.6717
Max Act: 7.9842. Min Act: -0.1700
Data Index: 1171990 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6717. Min Range: -8.6717
Max Act: 7.9842. Min Act: -0.1700
Data Index: 401183 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6717. Min Range: -8.6717
Max Act: 7.9842. Min Act: -0.1700
Data Index: 6151037 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6717. Min Range: -8.6717
Max Act: 7.9842. Min Act: -0.1700
Data Index: 7646261 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6717. Min Range: -8.6717
Max Act: 7.9217. Min Act: -0.1700
Data Index: 3875237 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6717. Min Range: -8.6717
Max Act: 7.9842. Min Act: -0.1700
Data Index: 3293847 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6717. Min Range: -8.6717
Max Act: 7.9217. Min Act: -0.1700
Data Index: 3146489 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6717. Min Range: -8.6717
Max Act: 7.9217. Min Act: -0.1700
Data Index: 4990108 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6717. Min Range: -8.6717
Max Act: 7.8592. Min Act: -0.1700
Data Index: 657491 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6717. Min Range: -8.6717
Max Act: 7.8592. Min Act: -0.1700
Data Index: 6781774 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6717. Min Range: -8.6717
Max Act: 7.7967. Min Act: -0.1700
Data Index: 2726190 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6717. Min Range: -8.6717
Max Act: 7.7967. Min Act: -0.1700
Data Index: 6856677 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19