Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4117. Min Range: -7.4117
Max Act: 7.4117. Min Act: -0.1700
Data Index: 2378983 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4117. Min Range: -7.4117
Max Act: 7.2554. Min Act: -0.1700
Data Index: 912601 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4117. Min Range: -7.4117
Max Act: 7.1617. Min Act: -0.1700
Data Index: 2752596 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.9429. Min Act: -0.1700
Data Index: 772303 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.8492. Min Act: -0.1700
Data Index: 5820236 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.8492. Min Act: -0.1700
Data Index: 6493692 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.5367. Min Act: -0.1700
Data Index: 6564700 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.5054. Min Act: -0.1700
Data Index: 1481141 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.5367. Min Act: -0.1700
Data Index: 7870998 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.5054. Min Act: -0.1700
Data Index: 5544874 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.4742. Min Act: -0.1700
Data Index: 4054862 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.4742. Min Act: -0.1700
Data Index: 3469798 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.4429. Min Act: -0.1700
Data Index: 8088349 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.4429. Min Act: -0.1700
Data Index: 748077 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.4429. Min Act: -0.1700
Data Index: 384704 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.4117. Min Act: -0.1700
Data Index: 6821083 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.4117. Min Act: -0.1700
Data Index: 4074175 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.3804. Min Act: -0.1700
Data Index: 4958534 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.3804. Min Act: -0.1700
Data Index: 1700984 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4117. Min Range: -7.4117
Max Act: 6.3804. Min Act: -0.1700
Data Index: 2548577 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19