Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1030 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.6002. Min Act: -0.1700
Data Index: 6058844 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.4440. Min Act: -0.1700
Data Index: 4825083 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.3815. Min Act: -0.1700
Data Index: 7779190 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.3190. Min Act: -0.1700
Data Index: 3786886 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.2252. Min Act: -0.1700
Data Index: 2908504 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.1940. Min Act: -0.1700
Data Index: 3240560 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.1627. Min Act: -0.1700
Data Index: 180434 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.1627. Min Act: -0.1700
Data Index: 6216876 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.1627. Min Act: -0.1700
Data Index: 404850 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.1315. Min Act: -0.1700
Data Index: 5026401 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.1315. Min Act: -0.1700
Data Index: 1753444 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.1315. Min Act: -0.1700
Data Index: 2199752 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.1315. Min Act: -0.1700
Data Index: 8473658 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.0690. Min Act: -0.1700
Data Index: 4269525 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.0690. Min Act: -0.1700
Data Index: 5499339 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.0377. Min Act: -0.1700
Data Index: 8108851 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6002. Min Range: -6.6002
Max Act: 6.0065. Min Act: -0.1700
Data Index: 3763517 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6002. Min Range: -6.6002
Max Act: 5.9440. Min Act: -0.1700
Data Index: 5619463 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6002. Min Range: -6.6002
Max Act: 5.9440. Min Act: -0.1700
Data Index: 4458316 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6002. Min Range: -6.6002
Max Act: 5.9440. Min Act: -0.1700
Data Index: 8175751 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19