Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0391. Min Range: -6.0391
Max Act: 6.0391. Min Act: -0.1700
Data Index: 6085700 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.6953. Min Act: -0.1700
Data Index: 7618734 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.4453. Min Act: -0.1700
Data Index: 1458663 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.4141. Min Act: -0.1700
Data Index: 7251012 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.3828. Min Act: -0.1700
Data Index: 1100335 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.3828. Min Act: -0.1696
Data Index: 5270798 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.3828. Min Act: -0.1700
Data Index: 1653922 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.3516. Min Act: -0.1700
Data Index: 7891952 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.3203. Min Act: -0.1700
Data Index: 4889669 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.3203. Min Act: -0.1700
Data Index: 2370134 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.2891. Min Act: -0.1700
Data Index: 7618735 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.2578. Min Act: -0.1700
Data Index: 6143737 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.2266. Min Act: -0.1700
Data Index: 320915 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.2266. Min Act: -0.1700
Data Index: 3541194 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.1641. Min Act: -0.1700
Data Index: 8099978 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.1641. Min Act: -0.1700
Data Index: 6232345 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.1641. Min Act: -0.1700
Data Index: 719345 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.1328. Min Act: -0.1700
Data Index: 2977548 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.1641. Min Act: -0.1700
Data Index: 1458093 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0391. Min Range: -6.0391
Max Act: 5.1016. Min Act: -0.1700
Data Index: 5025582 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19