Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3232 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.4737. Min Act: -0.1700
Data Index: 8274555 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.4425. Min Act: -0.1700
Data Index: 739365 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.3800. Min Act: -0.1700
Data Index: 7937916 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.3800. Min Act: -0.1700
Data Index: 1161649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.3487. Min Act: -0.1700
Data Index: 1728015 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.3487. Min Act: -0.1700
Data Index: 8721964 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.3175. Min Act: -0.1700
Data Index: 5851983 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.3175. Min Act: -0.1700
Data Index: 7637821 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.3175. Min Act: -0.1700
Data Index: 1904572 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.3175. Min Act: -0.1700
Data Index: 4295981 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.3175. Min Act: -0.1700
Data Index: 4145757 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.2862. Min Act: -0.1700
Data Index: 490424 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.2862. Min Act: -0.1700
Data Index: 5989515 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.2862. Min Act: -0.1700
Data Index: 172138 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.2862. Min Act: -0.1700
Data Index: 4979714 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.2862. Min Act: -0.1700
Data Index: 6777002 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.2550. Min Act: -0.1700
Data Index: 534008 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.2550. Min Act: -0.1700
Data Index: 5857733 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.2550. Min Act: -0.1700
Data Index: 1896676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4737. Min Range: -4.4737
Max Act: 4.2862. Min Act: -0.1700
Data Index: 6834007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19