Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2612 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.5410. Min Act: -0.1700
Data Index: 4977418 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.5410. Min Act: -0.1700
Data Index: 2476602 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.5098. Min Act: -0.1700
Data Index: 5878726 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.5098. Min Act: -0.1700
Data Index: 1184064 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.5098. Min Act: -0.1700
Data Index: 3611624 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.5098. Min Act: -0.1700
Data Index: 7274098 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.4785. Min Act: -0.1700
Data Index: 898014 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.4473. Min Act: -0.1700
Data Index: 662418 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.4473. Min Act: -0.1700
Data Index: 6200880 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.3848. Min Act: -0.1700
Data Index: 2130668 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.4473. Min Act: -0.1700
Data Index: 3874944 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.4473. Min Act: -0.1700
Data Index: 4402096 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.4160. Min Act: -0.1700
Data Index: 740169 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.3848. Min Act: -0.1700
Data Index: 5918876 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.3848. Min Act: -0.1700
Data Index: 3922038 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.3535. Min Act: -0.1700
Data Index: 1659859 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.3535. Min Act: -0.1700
Data Index: 4484257 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.3535. Min Act: -0.1700
Data Index: 1765566 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.3223. Min Act: -0.1700
Data Index: 705255 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5410. Min Range: -5.5410
Max Act: 5.3223. Min Act: -0.1700
Data Index: 2159600 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19