Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1342. Min Range: -5.1342
Max Act: 5.1342. Min Act: -0.1700
Data Index: 4441873 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1342. Min Range: -5.1342
Max Act: 5.1342. Min Act: -0.1700
Data Index: 7177478 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1342. Min Range: -5.1342
Max Act: 5.1030. Min Act: -0.1700
Data Index: 3502112 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1342. Min Range: -5.1342
Max Act: 5.0092. Min Act: -0.1700
Data Index: 2130672 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1342. Min Range: -5.1342
Max Act: 5.0405. Min Act: -0.1700
Data Index: 2282425 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.9780. Min Act: -0.1700
Data Index: 1630253 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.9780. Min Act: -0.1700
Data Index: 3223948 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.9467. Min Act: -0.1700
Data Index: 2850795 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.9467. Min Act: -0.1700
Data Index: 6970853 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.9155. Min Act: -0.1700
Data Index: 5966449 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.9155. Min Act: -0.1700
Data Index: 5287971 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.9155. Min Act: -0.1700
Data Index: 5152072 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.8842. Min Act: -0.1700
Data Index: 1884594 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.8842. Min Act: -0.1700
Data Index: 5395167 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.8530. Min Act: -0.1700
Data Index: 558307 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.8530. Min Act: -0.1700
Data Index: 7901294 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.8530. Min Act: -0.1700
Data Index: 604694 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.8530. Min Act: -0.1700
Data Index: 1956206 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.8530. Min Act: -0.1700
Data Index: 7301389 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1342. Min Range: -5.1342
Max Act: 4.8217. Min Act: -0.1700
Data Index: 1200576 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19