Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5055 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.4204. Min Act: -0.1700
Data Index: 521630 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.4204. Min Act: -0.1700
Data Index: 6611758 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.3892. Min Act: -0.1700
Data Index: 1077845 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.3267. Min Act: -0.1700
Data Index: 6087511 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.3579. Min Act: -0.1700
Data Index: 1703010 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.3579. Min Act: -0.1700
Data Index: 4878264 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.3267. Min Act: -0.1700
Data Index: 2301653 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.2642. Min Act: -0.1700
Data Index: 5309888 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.2329. Min Act: -0.1700
Data Index: 423619 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.2329. Min Act: -0.1700
Data Index: 5732163 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.2329. Min Act: -0.1700
Data Index: 1489181 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.2329. Min Act: -0.1700
Data Index: 3651993 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.2017. Min Act: -0.1700
Data Index: 7136665 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.1704. Min Act: -0.1700
Data Index: 3040841 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.1704. Min Act: -0.1700
Data Index: 4378855 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.1704. Min Act: -0.1700
Data Index: 6788023 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.1704. Min Act: -0.1700
Data Index: 4176027 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.2017. Min Act: -0.1700
Data Index: 5460925 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.1704. Min Act: -0.1700
Data Index: 2196976 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4204. Min Range: -5.4204
Max Act: 5.1704. Min Act: -0.1700
Data Index: 1079778 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19