Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2963 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.7027. Min Act: -0.1700
Data Index: 5618451 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.6714. Min Act: -0.1700
Data Index: 1185751 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.5777. Min Act: -0.1700
Data Index: 1025844 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.6089. Min Act: -0.1700
Data Index: 5736332 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.5777. Min Act: -0.1700
Data Index: 6396743 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.5464. Min Act: -0.1700
Data Index: 6572976 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.4839. Min Act: -0.1700
Data Index: 1229669 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.4527. Min Act: -0.1700
Data Index: 4434582 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.4839. Min Act: -0.1700
Data Index: 7186682 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.4839. Min Act: -0.1700
Data Index: 8809167 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.4839. Min Act: -0.1700
Data Index: 836397 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.4839. Min Act: -0.1700
Data Index: 4420592 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.4527. Min Act: -0.1700
Data Index: 8798624 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.4527. Min Act: -0.1700
Data Index: 4997662 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.3902. Min Act: -0.1700
Data Index: 852264 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.4214. Min Act: -0.1700
Data Index: 4702614 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.4214. Min Act: -0.1700
Data Index: 4158734 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.4214. Min Act: -0.1700
Data Index: 2069731 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.3902. Min Act: -0.1700
Data Index: 6434044 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7027. Min Range: -5.7027
Max Act: 5.4214. Min Act: -0.1700
Data Index: 3623500 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19