Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7872. Min Act: -0.1700
Data Index: 2646767 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7872. Min Act: -0.1700
Data Index: 3650568 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7560. Min Act: -0.1700
Data Index: 4022390 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7560. Min Act: -0.1700
Data Index: 1226559 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7560. Min Act: -0.1700
Data Index: 1440758 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7560. Min Act: -0.1700
Data Index: 2135244 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 5862739 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 1632231 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 7379535 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 3593725 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7560. Min Act: -0.1700
Data Index: 7003682 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 6720126 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 5891114 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 895063 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 3319172 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 2708307 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 5587048 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 180834 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 2293832 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7872. Min Range: -4.7872
Max Act: 4.7247. Min Act: -0.1700
Data Index: 3875622 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19