Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.8036. Min Act: -0.1700
Data Index: 6286183 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.6474. Min Act: -0.1700
Data Index: 938669 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.4911. Min Act: -0.1700
Data Index: 5973366 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.4286. Min Act: -0.1700
Data Index: 7800013 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.3974. Min Act: -0.1700
Data Index: 4134775 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.3661. Min Act: -0.1700
Data Index: 5233394 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.3349. Min Act: -0.1700
Data Index: 8698791 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.2724. Min Act: -0.1700
Data Index: 6286021 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.2099. Min Act: -0.1700
Data Index: 7777504 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.2099. Min Act: -0.1700
Data Index: 1057331 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.2099. Min Act: -0.1700
Data Index: 1421774 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.2099. Min Act: -0.1700
Data Index: 1274876 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.1786. Min Act: -0.1700
Data Index: 2220998 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.1474. Min Act: -0.1700
Data Index: 3970241 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.1786. Min Act: -0.1700
Data Index: 3371018 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.1786. Min Act: -0.1700
Data Index: 4486928 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.1786. Min Act: -0.1700
Data Index: 3499585 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.1786. Min Act: -0.1700
Data Index: 8070641 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.1786. Min Act: -0.1700
Data Index: 3937689 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8036. Min Range: -5.8036
Max Act: 5.1474. Min Act: -0.1700
Data Index: 5332215 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19