Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.8467. Min Act: -0.1700
Data Index: 1986936 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.8154. Min Act: -0.1700
Data Index: 728660 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.8467. Min Act: -0.1700
Data Index: 7119396 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.8154. Min Act: -0.1700
Data Index: 6509522 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7842. Min Act: -0.1699
Data Index: 5495413 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7842. Min Act: -0.1700
Data Index: 8198325 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.8154. Min Act: -0.1700
Data Index: 3290296 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7842. Min Act: -0.1700
Data Index: 3552042 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7842. Min Act: -0.1700
Data Index: 2132699 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7842. Min Act: -0.1700
Data Index: 5946792 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7842. Min Act: -0.1700
Data Index: 6310963 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7842. Min Act: -0.1700
Data Index: 7069694 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7529. Min Act: -0.1700
Data Index: 1814237 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7529. Min Act: -0.1700
Data Index: 3663066 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7217. Min Act: -0.1700
Data Index: 7119395 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7529. Min Act: -0.1700
Data Index: 5864790 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7529. Min Act: -0.1700
Data Index: 191560 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7529. Min Act: -0.1700
Data Index: 5622857 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7529. Min Act: -0.1700
Data Index: 164117 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7529. Min Act: -0.1700
Data Index: 3614041 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19