Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2587 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.4504. Min Act: -0.1700
Data Index: 5427279 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.4504. Min Act: -0.1700
Data Index: 8442110 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.4817. Min Act: -0.1700
Data Index: 4286231 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.4504. Min Act: -0.1700
Data Index: 7309414 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3879. Min Act: -0.1700
Data Index: 4375543 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3879. Min Act: -0.1700
Data Index: 2763039 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.4192. Min Act: -0.1700
Data Index: 2274091 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3567. Min Act: -0.1700
Data Index: 2814047 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3567. Min Act: -0.1700
Data Index: 986504 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3567. Min Act: -0.1700
Data Index: 815865 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3567. Min Act: -0.1700
Data Index: 1926086 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3254. Min Act: -0.1700
Data Index: 2273727 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3254. Min Act: -0.1700
Data Index: 3796529 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3254. Min Act: -0.1700
Data Index: 8725009 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3254. Min Act: -0.1700
Data Index: 5282866 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3254. Min Act: -0.1700
Data Index: 1472118 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3254. Min Act: -0.1700
Data Index: 2886513 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3254. Min Act: -0.1700
Data Index: 7988108 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.3254. Min Act: -0.1700
Data Index: 7838265 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.2629. Min Act: -0.1700
Data Index: 6943930 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19