Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5764 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5008. Min Range: -6.5008
Max Act: 6.5008. Min Act: -0.1700
Data Index: 1701869 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5008. Min Range: -6.5008
Max Act: 6.1571. Min Act: -0.1700
Data Index: 6952586 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.8758. Min Act: -0.1700
Data Index: 2919218 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.8133. Min Act: -0.1700
Data Index: 5866951 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.6571. Min Act: -0.1700
Data Index: 201351 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.6258. Min Act: -0.1700
Data Index: 5483928 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.6258. Min Act: -0.1700
Data Index: 1725357 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.5946. Min Act: -0.1700
Data Index: 6566018 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.5321. Min Act: -0.1700
Data Index: 1623657 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.5008. Min Act: -0.1700
Data Index: 5897947 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.5008. Min Act: -0.1700
Data Index: 8737728 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.4383. Min Act: -0.1700
Data Index: 2471165 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.4696. Min Act: -0.1700
Data Index: 8086997 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.4696. Min Act: -0.1700
Data Index: 4601874 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.5008. Min Act: -0.1700
Data Index: 2650821 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.4383. Min Act: -0.1700
Data Index: 8125970 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.4383. Min Act: -0.1700
Data Index: 4284121 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.4383. Min Act: -0.1700
Data Index: 2946416 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.4071. Min Act: -0.1700
Data Index: 397492 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5008. Min Range: -6.5008
Max Act: 5.4071. Min Act: -0.1700
Data Index: 5347415 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19