Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1287 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1015. Min Range: -5.1015
Max Act: 5.1015. Min Act: -0.1700
Data Index: 468360 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.8202. Min Act: -0.1700
Data Index: 5603707 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.7890. Min Act: -0.1700
Data Index: 5316009 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.6952. Min Act: -0.1700
Data Index: 5806050 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.6952. Min Act: -0.1700
Data Index: 4607986 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.6640. Min Act: -0.1700
Data Index: 4847960 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.6327. Min Act: -0.1700
Data Index: 7061568 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.6327. Min Act: -0.1700
Data Index: 4473965 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.6015. Min Act: -0.1700
Data Index: 5081328 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.5702. Min Act: -0.1700
Data Index: 4368367 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.5702. Min Act: -0.1700
Data Index: 4492780 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.5702. Min Act: -0.1700
Data Index: 6078846 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.6015. Min Act: -0.1700
Data Index: 6047435 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.5390. Min Act: -0.1700
Data Index: 4705361 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.5390. Min Act: -0.1700
Data Index: 7928153 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.5390. Min Act: -0.1700
Data Index: 4173383 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.5077. Min Act: -0.1700
Data Index: 3050884 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.5077. Min Act: -0.1700
Data Index: 4211596 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.5077. Min Act: -0.1700
Data Index: 7959186 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1015. Min Range: -5.1015
Max Act: 4.4765. Min Act: -0.1700
Data Index: 230125 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19