Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5804 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.5567. Min Act: -0.1700
Data Index: 332198 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.5567. Min Act: -0.1700
Data Index: 2871934 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.4317. Min Act: -0.1700
Data Index: 6273331 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.2442. Min Act: -0.1700
Data Index: 6273323 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.2442. Min Act: -0.1700
Data Index: 2871936 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.1817. Min Act: -0.1700
Data Index: 298182 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.2442. Min Act: -0.1700
Data Index: 5470974 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.1817. Min Act: -0.1700
Data Index: 8146797 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.1817. Min Act: -0.1700
Data Index: 1963818 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.1192. Min Act: -0.1700
Data Index: 4120898 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.1192. Min Act: -0.1700
Data Index: 6996505 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.1192. Min Act: -0.1700
Data Index: 8569854 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.1192. Min Act: -0.1700
Data Index: 8069713 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.0254. Min Act: -0.1700
Data Index: 496366 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.0567. Min Act: -0.1700
Data Index: 484465 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.0254. Min Act: -0.1700
Data Index: 1967755 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.0254. Min Act: -0.1700
Data Index: 3438456 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.0254. Min Act: -0.1700
Data Index: 621637 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5567. Min Range: -8.5567
Max Act: 8.0254. Min Act: -0.1700
Data Index: 2130670 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5567. Min Range: -8.5567
Max Act: 7.9942. Min Act: -0.1700
Data Index: 1967759 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19