Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2882 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.6018. Min Act: -0.1700
Data Index: 178559 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.5081. Min Act: -0.1700
Data Index: 3195509 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.3831. Min Act: -0.1700
Data Index: 7165044 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.3206. Min Act: -0.1700
Data Index: 451726 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.2581. Min Act: -0.1700
Data Index: 733481 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.2893. Min Act: -0.1700
Data Index: 6517899 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.2581. Min Act: -0.1700
Data Index: 5011536 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.2893. Min Act: -0.1700
Data Index: 6613327 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.1018. Min Act: -0.1700
Data Index: 2712389 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.1018. Min Act: -0.1700
Data Index: 331160 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.1018. Min Act: -0.1700
Data Index: 1928581 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.0706. Min Act: -0.1700
Data Index: 5144058 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.1018. Min Act: -0.1700
Data Index: 4925766 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.1018. Min Act: -0.1700
Data Index: 65792 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.0706. Min Act: -0.1700
Data Index: 2075848 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.0706. Min Act: -0.1700
Data Index: 7940120 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6018. Min Range: -6.6018
Max Act: 6.0081. Min Act: -0.1700
Data Index: 6063693 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6018. Min Range: -6.6018
Max Act: 5.9456. Min Act: -0.1700
Data Index: 8142868 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6018. Min Range: -6.6018
Max Act: 5.9143. Min Act: -0.1700
Data Index: 5111153 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6018. Min Range: -6.6018
Max Act: 5.8831. Min Act: -0.1700
Data Index: 3392001 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19