Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4421 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.5119. Min Act: -0.1700
Data Index: 7328745 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.4806. Min Act: -0.1700
Data Index: 2485541 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.4181. Min Act: -0.1700
Data Index: 80360 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.3556. Min Act: -0.1700
Data Index: 3644639 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.3556. Min Act: -0.1700
Data Index: 8780068 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.3556. Min Act: -0.1700
Data Index: 1273495 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.3556. Min Act: -0.1700
Data Index: 7571141 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.3244. Min Act: -0.1700
Data Index: 1034090 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.3244. Min Act: -0.1700
Data Index: 4450755 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.3244. Min Act: -0.1700
Data Index: 3953045 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.2931. Min Act: -0.1700
Data Index: 3953041 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.2931. Min Act: -0.1700
Data Index: 230134 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.2931. Min Act: -0.1700
Data Index: 3953036 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.2931. Min Act: -0.1700
Data Index: 4150922 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.2931. Min Act: -0.1700
Data Index: 5871206 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.2931. Min Act: -0.1700
Data Index: 7806057 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.2931. Min Act: -0.1700
Data Index: 4450760 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.2619. Min Act: -0.1700
Data Index: 733330 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.3244. Min Act: -0.1700
Data Index: 4450759 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5119. Min Range: -5.5119
Max Act: 5.2619. Min Act: -0.1700
Data Index: 3953037 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19