Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1517. Min Range: -5.1517
Max Act: 5.1517. Min Act: -0.1700
Data Index: 1161677 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1517. Min Range: -5.1517
Max Act: 5.1204. Min Act: -0.1700
Data Index: 1270973 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1517. Min Range: -5.1517
Max Act: 5.0579. Min Act: -0.1700
Data Index: 2751745 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.9954. Min Act: -0.1700
Data Index: 1523588 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.9954. Min Act: -0.1700
Data Index: 2580981 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.9954. Min Act: -0.1700
Data Index: 231317 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.9642. Min Act: -0.1700
Data Index: 1123051 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.9642. Min Act: -0.1700
Data Index: 4246670 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.9642. Min Act: -0.1700
Data Index: 8490125 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.9642. Min Act: -0.1700
Data Index: 4596667 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.9329. Min Act: -0.1700
Data Index: 4170421 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.9329. Min Act: -0.1700
Data Index: 2951524 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.9329. Min Act: -0.1700
Data Index: 402510 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.9017. Min Act: -0.1700
Data Index: 7806508 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.8704. Min Act: -0.1700
Data Index: 6039916 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.8704. Min Act: -0.1700
Data Index: 4836763 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.8704. Min Act: -0.1700
Data Index: 634619 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.8704. Min Act: -0.1700
Data Index: 6726217 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.8704. Min Act: -0.1700
Data Index: 983071 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1517. Min Range: -5.1517
Max Act: 4.8392. Min Act: -0.1700
Data Index: 6274300 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19