Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5149 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.4789. Min Act: -0.1700
Data Index: 1327569 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.5101. Min Act: -0.1700
Data Index: 3564762 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.4789. Min Act: -0.1700
Data Index: 8311554 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.4476. Min Act: -0.1700
Data Index: 6656500 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.3539. Min Act: -0.1700
Data Index: 3968448 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2914. Min Act: -0.1700
Data Index: 678882 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2914. Min Act: -0.1700
Data Index: 8632137 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.3226. Min Act: -0.1700
Data Index: 264969 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2601. Min Act: -0.1700
Data Index: 2897274 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2601. Min Act: -0.1700
Data Index: 8247765 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2289. Min Act: -0.1700
Data Index: 2490971 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2601. Min Act: -0.1700
Data Index: 8121563 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2601. Min Act: -0.1700
Data Index: 1850549 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2601. Min Act: -0.1700
Data Index: 6778829 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2601. Min Act: -0.1700
Data Index: 4312193 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2289. Min Act: -0.1700
Data Index: 555636 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2289. Min Act: -0.1700
Data Index: 3069411 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2289. Min Act: -0.1700
Data Index: 3323752 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.2289. Min Act: -0.1700
Data Index: 8516564 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5101. Min Range: -6.5101
Max Act: 6.1976. Min Act: -0.1700
Data Index: 917835 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19