Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.5650. Min Act: -0.1700
Data Index: 5358396 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.5338. Min Act: -0.1700
Data Index: 3552186 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.4400. Min Act: -0.1700
Data Index: 610005 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.3775. Min Act: -0.1700
Data Index: 5672543 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.4088. Min Act: -0.1700
Data Index: 4562568 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.3463. Min Act: -0.1700
Data Index: 1352932 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.3775. Min Act: -0.1700
Data Index: 1262007 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.3150. Min Act: -0.1700
Data Index: 7788163 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.2838. Min Act: -0.1700
Data Index: 5417863 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.2838. Min Act: -0.1700
Data Index: 5490342 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.2838. Min Act: -0.1700
Data Index: 1059767 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.3150. Min Act: -0.1700
Data Index: 8531951 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.2525. Min Act: -0.1700
Data Index: 4666046 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.2213. Min Act: -0.1700
Data Index: 5920069 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.2213. Min Act: -0.1700
Data Index: 3132016 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.2213. Min Act: -0.1700
Data Index: 7083624 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.2213. Min Act: -0.1700
Data Index: 4047843 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.1900. Min Act: -0.1700
Data Index: 5368003 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.1900. Min Act: -0.1700
Data Index: 985701 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5650. Min Range: -5.5650
Max Act: 5.1900. Min Act: -0.1700
Data Index: 2248160 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19