Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1784 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.2848. Min Act: -0.1700
Data Index: 3800470 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.1590. Min Act: -0.1700
Data Index: 1609926 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.1905. Min Act: -0.1700
Data Index: 8172028 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.1748. Min Act: -0.1700
Data Index: 2783244 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.1748. Min Act: -0.1700
Data Index: 5912247 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.1590. Min Act: -0.1700
Data Index: 4843305 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.1590. Min Act: -0.1700
Data Index: 5311937 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.1275. Min Act: -0.1700
Data Index: 939018 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.1118. Min Act: -0.1700
Data Index: 2414220 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.1118. Min Act: -0.1700
Data Index: 2993342 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.0960. Min Act: -0.1700
Data Index: 5080420 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.0960. Min Act: -0.1700
Data Index: 4967117 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.0803. Min Act: -0.1700
Data Index: 3183816 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.0803. Min Act: -0.1700
Data Index: 5212801 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.0803. Min Act: -0.1700
Data Index: 7004385 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.0645. Min Act: -0.1700
Data Index: 4352170 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.0487. Min Act: -0.1700
Data Index: 6406517 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.0329. Min Act: -0.1700
Data Index: 4365752 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.0487. Min Act: -0.1700
Data Index: 8006958 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2848. Min Range: -3.2848
Max Act: 3.0487. Min Act: -0.1700
Data Index: 8079323 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19