Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 78 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.7251. Min Act: -0.1700
Data Index: 6053700 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.4751. Min Act: -0.1700
Data Index: 6092437 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.4751. Min Act: -0.1700
Data Index: 6887097 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.4439. Min Act: -0.1700
Data Index: 5571958 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.4439. Min Act: -0.1700
Data Index: 5078950 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.4126. Min Act: -0.1700
Data Index: 297227 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.3814. Min Act: -0.1700
Data Index: 98356 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.3814. Min Act: -0.1700
Data Index: 5113114 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.3814. Min Act: -0.1700
Data Index: 5528830 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.3189. Min Act: -0.1700
Data Index: 3151471 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.2876. Min Act: -0.1700
Data Index: 6711054 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.3189. Min Act: -0.1700
Data Index: 8027653 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.3189. Min Act: -0.1700
Data Index: 1569783 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.2876. Min Act: -0.1700
Data Index: 4052097 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.2564. Min Act: -0.1700
Data Index: 5294375 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.2564. Min Act: -0.1700
Data Index: 6174239 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.2564. Min Act: -0.1700
Data Index: 8738604 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.2251. Min Act: -0.1700
Data Index: 4120087 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.2251. Min Act: -0.1700
Data Index: 2999486 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7251. Min Range: -5.7251
Max Act: 5.1939. Min Act: -0.1700
Data Index: 664969 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19