Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5167 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.3255. Min Act: -0.1700
Data Index: 7026683 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.2630. Min Act: -0.1700
Data Index: 5732665 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.2630. Min Act: -0.1700
Data Index: 7886558 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.2630. Min Act: -0.1700
Data Index: 8379767 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.2318. Min Act: -0.1700
Data Index: 4837107 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.2318. Min Act: -0.1700
Data Index: 2214079 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.2005. Min Act: -0.1700
Data Index: 1406971 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.2005. Min Act: -0.1700
Data Index: 892752 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.1693. Min Act: -0.1700
Data Index: 3294161 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.1693. Min Act: -0.1700
Data Index: 2859839 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.1693. Min Act: -0.1700
Data Index: 3405262 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.1380. Min Act: -0.1700
Data Index: 6354861 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.1693. Min Act: -0.1700
Data Index: 3877858 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.1380. Min Act: -0.1700
Data Index: 4517429 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.1380. Min Act: -0.1700
Data Index: 1267115 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.1380. Min Act: -0.1700
Data Index: 1317115 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.1380. Min Act: -0.1700
Data Index: 1047708 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.1068. Min Act: -0.1700
Data Index: 1406973 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.1068. Min Act: -0.1700
Data Index: 2509658 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3255. Min Range: -5.3255
Max Act: 5.1068. Min Act: -0.1700
Data Index: 1922873 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19