Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1778 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.9676. Min Act: -0.1700
Data Index: 3990651 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.9363. Min Act: -0.1700
Data Index: 1972765 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.8738. Min Act: -0.1700
Data Index: 6276768 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.8426. Min Act: -0.1700
Data Index: 7263383 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.8426. Min Act: -0.1700
Data Index: 6081511 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.7801. Min Act: -0.1700
Data Index: 2901036 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.7488. Min Act: -0.1700
Data Index: 7264071 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.7176. Min Act: -0.1700
Data Index: 1405816 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.7176. Min Act: -0.1700
Data Index: 5612820 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.6863. Min Act: -0.1700
Data Index: 1209202 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.6863. Min Act: -0.1700
Data Index: 5565936 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.6551. Min Act: -0.1700
Data Index: 1654575 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.6551. Min Act: -0.1700
Data Index: 7644831 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.6238. Min Act: -0.1700
Data Index: 5664133 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.5926. Min Act: -0.1700
Data Index: 4549966 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.5926. Min Act: -0.1700
Data Index: 3542674 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.5926. Min Act: -0.1700
Data Index: 4562212 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.5926. Min Act: -0.1700
Data Index: 7699652 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.5613. Min Act: -0.1700
Data Index: 626270 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.5613. Min Act: -0.1700
Data Index: 5286426 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19