Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1690 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2926. Min Range: -6.2926
Max Act: 6.2926. Min Act: -0.1700
Data Index: 772351 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2926. Min Range: -6.2926
Max Act: 6.2613. Min Act: -0.1700
Data Index: 2595908 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2926. Min Range: -6.2926
Max Act: 6.1988. Min Act: -0.1700
Data Index: 2827014 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2926. Min Range: -6.2926
Max Act: 6.1676. Min Act: -0.1700
Data Index: 3477856 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2926. Min Range: -6.2926
Max Act: 6.1363. Min Act: -0.1700
Data Index: 4698450 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2926. Min Range: -6.2926
Max Act: 6.0738. Min Act: -0.1700
Data Index: 6951719 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2926. Min Range: -6.2926
Max Act: 6.0426. Min Act: -0.1700
Data Index: 1634916 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2926. Min Range: -6.2926
Max Act: 6.0426. Min Act: -0.1700
Data Index: 2094772 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2926. Min Range: -6.2926
Max Act: 6.0113. Min Act: -0.1700
Data Index: 3865545 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2926. Min Range: -6.2926
Max Act: 5.9801. Min Act: -0.1700
Data Index: 4599366 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2926. Min Range: -6.2926
Max Act: 6.0113. Min Act: -0.1700
Data Index: 932240 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2926. Min Range: -6.2926
Max Act: 6.0113. Min Act: -0.1700
Data Index: 3591857 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2926. Min Range: -6.2926
Max Act: 5.9801. Min Act: -0.1700
Data Index: 3393283 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2926. Min Range: -6.2926
Max Act: 5.9801. Min Act: -0.1700
Data Index: 3869615 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2926. Min Range: -6.2926
Max Act: 5.9801. Min Act: -0.1700
Data Index: 8384589 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2926. Min Range: -6.2926
Max Act: 5.9176. Min Act: -0.1700
Data Index: 7050376 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2926. Min Range: -6.2926
Max Act: 5.9176. Min Act: -0.1700
Data Index: 3149977 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2926. Min Range: -6.2926
Max Act: 5.9176. Min Act: -0.1700
Data Index: 450415 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2926. Min Range: -6.2926
Max Act: 5.8863. Min Act: -0.1700
Data Index: 4540305 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2926. Min Range: -6.2926
Max Act: 5.8551. Min Act: -0.1700
Data Index: 1005761 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19