Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3947 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.9704. Min Act: -0.1700
Data Index: 2598782 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0329. Min Range: -8.0329
Max Act: 8.0329. Min Act: -0.1700
Data Index: 869404 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.9079. Min Act: -0.1700
Data Index: 7492093 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.9079. Min Act: -0.1700
Data Index: 7736969 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.7517. Min Act: -0.1700
Data Index: 8163223 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.6892. Min Act: -0.1700
Data Index: 3334788 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.6892. Min Act: -0.1700
Data Index: 5227964 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.5954. Min Act: -0.1700
Data Index: 712479 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.5329. Min Act: -0.1700
Data Index: 259552 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.5017. Min Act: -0.1700
Data Index: 7251263 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.4079. Min Act: -0.1700
Data Index: 444493 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.4079. Min Act: -0.1700
Data Index: 7708097 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.4704. Min Act: -0.1700
Data Index: 984302 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.4079. Min Act: -0.1700
Data Index: 5380533 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.3767. Min Act: -0.1700
Data Index: 3440048 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.3767. Min Act: -0.1700
Data Index: 1183491 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0329. Min Range: -8.0329
Max Act: 5.7829. Min Act: -0.1700
Data Index: 79089 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.2517. Min Act: -0.1700
Data Index: 4611536 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.1892. Min Act: -0.1700
Data Index: 1698401 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0329. Min Range: -8.0329
Max Act: 7.2204. Min Act: -0.1700
Data Index: 1140902 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19