Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.5755. Min Act: -0.1700
Data Index: 1607157 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.4192. Min Act: -0.1700
Data Index: 7546737 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.3880. Min Act: -0.1700
Data Index: 4452151 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.3880. Min Act: -0.1700
Data Index: 7425956 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.2630. Min Act: -0.1700
Data Index: 7244175 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.2630. Min Act: -0.1700
Data Index: 2335127 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.2630. Min Act: -0.1700
Data Index: 3598089 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.2317. Min Act: -0.1700
Data Index: 3169760 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.2317. Min Act: -0.1700
Data Index: 662295 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.2317. Min Act: -0.1700
Data Index: 798356 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.2317. Min Act: -0.1700
Data Index: 925974 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.2005. Min Act: -0.1700
Data Index: 6738196 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.2317. Min Act: -0.1700
Data Index: 6337444 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.2005. Min Act: -0.1700
Data Index: 4552434 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.2005. Min Act: -0.1700
Data Index: 1885996 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.2317. Min Act: -0.1700
Data Index: 5840155 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.1692. Min Act: -0.1700
Data Index: 6573326 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.1380. Min Act: -0.1700
Data Index: 6043511 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.1380. Min Act: -0.1700
Data Index: 5407016 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5755. Min Range: -4.5755
Max Act: 4.1380. Min Act: -0.1700
Data Index: 5746838 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19