Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 353 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.2704. Min Act: -0.1700
Data Index: 5982089 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.2704. Min Act: -0.1700
Data Index: 3949916 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.2704. Min Act: -0.1700
Data Index: 727709 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.2704. Min Act: -0.1700
Data Index: 6016257 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.2704. Min Act: -0.1700
Data Index: 1003866 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.2079. Min Act: -0.1700
Data Index: 1819621 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.1766. Min Act: -0.1700
Data Index: 7273198 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0828. Min Act: -0.1700
Data Index: 4528017 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0828. Min Act: -0.1700
Data Index: 991817 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0516. Min Act: -0.1700
Data Index: 4393715 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0203. Min Act: -0.1700
Data Index: 3755763 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0203. Min Act: -0.1700
Data Index: 3280547 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0203. Min Act: -0.1700
Data Index: 465680 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0203. Min Act: -0.1700
Data Index: 4450370 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0203. Min Act: -0.1700
Data Index: 3170918 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0203. Min Act: -0.1700
Data Index: 2458442 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0203. Min Act: -0.1700
Data Index: 266856 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0203. Min Act: -0.1700
Data Index: 2187557 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0203. Min Act: -0.1700
Data Index: 1923973 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2704. Min Range: -4.2704
Max Act: 4.0203. Min Act: -0.1700
Data Index: 177102 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19