Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5189 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1410. Min Range: -5.1410
Max Act: 5.1410. Min Act: -0.1700
Data Index: 3948258 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1410. Min Range: -5.1410
Max Act: 5.0785. Min Act: -0.1700
Data Index: 8282771 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1410. Min Range: -5.1410
Max Act: 5.0473. Min Act: -0.1700
Data Index: 5234932 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1410. Min Range: -5.1410
Max Act: 5.0473. Min Act: -0.1700
Data Index: 2070737 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1410. Min Range: -5.1410
Max Act: 5.0160. Min Act: -0.1700
Data Index: 8494473 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1410. Min Range: -5.1410
Max Act: 5.0160. Min Act: -0.1700
Data Index: 4701584 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.9848. Min Act: -0.1700
Data Index: 465736 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.9535. Min Act: -0.1700
Data Index: 5257103 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1410. Min Range: -5.1410
Max Act: 5.0160. Min Act: -0.1700
Data Index: 3754491 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.9848. Min Act: -0.1700
Data Index: 1519780 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.9848. Min Act: -0.1700
Data Index: 4018146 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.9223. Min Act: -0.1700
Data Index: 179708 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.9535. Min Act: -0.1700
Data Index: 1552450 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.9535. Min Act: -0.1700
Data Index: 3316091 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.9535. Min Act: -0.1700
Data Index: 859327 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.9535. Min Act: -0.1700
Data Index: 8464 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.9535. Min Act: -0.1700
Data Index: 1284987 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.9535. Min Act: -0.1700
Data Index: 6830931 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.8910. Min Act: -0.1700
Data Index: 2716494 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1410. Min Range: -5.1410
Max Act: 4.9223. Min Act: -0.1700
Data Index: 1840617 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19