Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4899 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.2321. Min Act: -0.1700
Data Index: 102688 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.2009. Min Act: -0.1700
Data Index: 1168594 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1696. Min Act: -0.1700
Data Index: 6415059 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1383. Min Act: -0.1700
Data Index: 4325591 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1383. Min Act: -0.1700
Data Index: 5500109 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1383. Min Act: -0.1700
Data Index: 2817460 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1071. Min Act: -0.1700
Data Index: 7942294 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1071. Min Act: -0.1700
Data Index: 1833934 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1071. Min Act: -0.1700
Data Index: 5410413 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1071. Min Act: -0.1700
Data Index: 621837 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1071. Min Act: -0.1700
Data Index: 3316193 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1071. Min Act: -0.1700
Data Index: 6571303 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1071. Min Act: -0.1700
Data Index: 5573473 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1071. Min Act: -0.1700
Data Index: 6212850 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.1071. Min Act: -0.1700
Data Index: 6588490 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.0446. Min Act: -0.1700
Data Index: 7406002 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.0758. Min Act: -0.1700
Data Index: 7053863 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.0446. Min Act: -0.1700
Data Index: 4590015 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.0446. Min Act: -0.1700
Data Index: 363216 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2321. Min Range: -4.2321
Max Act: 4.0446. Min Act: -0.1700
Data Index: 4738722 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19