Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0012. Min Range: -5.0012
Max Act: 5.0012. Min Act: -0.1700
Data Index: 2086876 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.9387. Min Act: -0.1700
Data Index: 3764419 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.9387. Min Act: -0.1700
Data Index: 951088 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.9387. Min Act: -0.1700
Data Index: 1379814 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.9387. Min Act: -0.1700
Data Index: 837067 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.9075. Min Act: -0.1700
Data Index: 7032681 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.9075. Min Act: -0.1700
Data Index: 5666441 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.9075. Min Act: -0.1700
Data Index: 4223484 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.9075. Min Act: -0.1700
Data Index: 1931079 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.9075. Min Act: -0.1700
Data Index: 3617517 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.9075. Min Act: -0.1700
Data Index: 3565677 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.8762. Min Act: -0.1700
Data Index: 2367722 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.8762. Min Act: -0.1700
Data Index: 2048127 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.8762. Min Act: -0.1700
Data Index: 6321703 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.8450. Min Act: -0.1700
Data Index: 563778 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.8450. Min Act: -0.1700
Data Index: 14286 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.8450. Min Act: -0.1700
Data Index: 3340542 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.8450. Min Act: -0.1700
Data Index: 2048128 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.8450. Min Act: -0.1700
Data Index: 951089 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0012. Min Range: -5.0012
Max Act: 4.8450. Min Act: -0.1700
Data Index: 1686040 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19