Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4560 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3987. Min Range: -7.3987
Max Act: 7.3987. Min Act: -0.1700
Data Index: 2931531 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3987. Min Range: -7.3987
Max Act: 7.3362. Min Act: -0.1700
Data Index: 4297215 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3987. Min Range: -7.3987
Max Act: 7.2737. Min Act: -0.1700
Data Index: 8688874 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3987. Min Range: -7.3987
Max Act: 7.1175. Min Act: -0.1700
Data Index: 24297 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3987. Min Range: -7.3987
Max Act: 7.1175. Min Act: -0.1700
Data Index: 1029599 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3987. Min Range: -7.3987
Max Act: 7.0550. Min Act: -0.1700
Data Index: 4279726 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3987. Min Range: -7.3987
Max Act: 7.0237. Min Act: -0.1700
Data Index: 4804350 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.9612. Min Act: -0.1700
Data Index: 4424734 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.9300. Min Act: -0.1700
Data Index: 4855386 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.9612. Min Act: -0.1700
Data Index: 4771554 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.9300. Min Act: -0.1700
Data Index: 375262 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8987. Min Act: -0.1700
Data Index: 6406542 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.9300. Min Act: -0.1700
Data Index: 1306659 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.9300. Min Act: -0.1700
Data Index: 6777589 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8987. Min Act: -0.1700
Data Index: 7784091 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8987. Min Act: -0.1700
Data Index: 1961689 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8987. Min Act: -0.1700
Data Index: 2671824 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8987. Min Act: -0.1700
Data Index: 776472 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8987. Min Act: -0.1700
Data Index: 3955285 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8987. Min Act: -0.1700
Data Index: 1179708 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19