Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.5581. Min Act: -0.1700
Data Index: 4144593 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.5581. Min Act: -0.1700
Data Index: 8534925 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.4956. Min Act: -0.1700
Data Index: 3168348 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.4643. Min Act: -0.1700
Data Index: 2574635 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.4643. Min Act: -0.1700
Data Index: 3628625 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.4018. Min Act: -0.1700
Data Index: 2146297 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.4018. Min Act: -0.1700
Data Index: 3441016 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.3706. Min Act: -0.1700
Data Index: 7940365 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.3393. Min Act: -0.1700
Data Index: 7981071 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.3081. Min Act: -0.1700
Data Index: 3546894 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.3393. Min Act: -0.1700
Data Index: 7442574 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.3081. Min Act: -0.1700
Data Index: 5866753 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.2768. Min Act: -0.1700
Data Index: 3096535 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.2768. Min Act: -0.1700
Data Index: 7079947 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.2768. Min Act: -0.1700
Data Index: 6807034 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.2768. Min Act: -0.1700
Data Index: 4199957 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.2768. Min Act: -0.1700
Data Index: 2845269 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.2768. Min Act: -0.1700
Data Index: 1294496 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.2143. Min Act: -0.1700
Data Index: 4665430 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5581. Min Range: -5.5581
Max Act: 5.2456. Min Act: -0.1700
Data Index: 1186954 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19