Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3545 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.9577. Min Act: -0.1700
Data Index: 6093712 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.8640. Min Act: -0.1700
Data Index: 6394487 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.8640. Min Act: -0.1700
Data Index: 3264724 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.8327. Min Act: -0.1700
Data Index: 7040261 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.8327. Min Act: -0.1700
Data Index: 5500405 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.8327. Min Act: -0.1700
Data Index: 5184419 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.8015. Min Act: -0.1700
Data Index: 3769300 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.8015. Min Act: -0.1700
Data Index: 6705479 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.8015. Min Act: -0.1700
Data Index: 1530744 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.8015. Min Act: -0.1700
Data Index: 5872514 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.7702. Min Act: -0.1700
Data Index: 7548259 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.7702. Min Act: -0.1700
Data Index: 4847209 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.7390. Min Act: -0.1700
Data Index: 8010836 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.7702. Min Act: -0.1700
Data Index: 7342978 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.7702. Min Act: -0.1700
Data Index: 3557277 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.7390. Min Act: -0.1700
Data Index: 5231578 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.7390. Min Act: -0.1700
Data Index: 7260281 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.7390. Min Act: -0.1700
Data Index: 3572560 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.7077. Min Act: -0.1700
Data Index: 6210937 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9577. Min Range: -4.9577
Max Act: 4.7077. Min Act: -0.1700
Data Index: 4793743 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19