Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6278 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1824. Min Range: -6.1824
Max Act: 6.1824. Min Act: -0.1700
Data Index: 6237407 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1824. Min Range: -6.1824
Max Act: 6.0887. Min Act: -0.1700
Data Index: 6999034 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1824. Min Range: -6.1824
Max Act: 6.0574. Min Act: -0.1700
Data Index: 2111646 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1824. Min Range: -6.1824
Max Act: 6.0262. Min Act: -0.1700
Data Index: 508162 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9949. Min Act: -0.1700
Data Index: 6190192 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9949. Min Act: -0.1700
Data Index: 2239473 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1824. Min Range: -6.1824
Max Act: 6.0262. Min Act: -0.1700
Data Index: 2544973 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9949. Min Act: -0.1700
Data Index: 4985235 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9637. Min Act: -0.1700
Data Index: 3344350 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9637. Min Act: -0.1700
Data Index: 7226902 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9637. Min Act: -0.1700
Data Index: 3095712 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9324. Min Act: -0.1700
Data Index: 938184 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9324. Min Act: -0.1700
Data Index: 8756540 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9012. Min Act: -0.1700
Data Index: 1633296 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.8699. Min Act: -0.1700
Data Index: 7391486 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.8699. Min Act: -0.1700
Data Index: 6382374 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.8699. Min Act: -0.1700
Data Index: 7998515 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.8699. Min Act: -0.1700
Data Index: 7595292 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.9012. Min Act: -0.1700
Data Index: 8688963 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1824. Min Range: -6.1824
Max Act: 5.8387. Min Act: -0.1700
Data Index: 671707 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19