Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 311 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4825. Min Range: -7.4825
Max Act: 7.4512. Min Act: -0.1700
Data Index: 5678412 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4825. Min Range: -7.4825
Max Act: 7.4825. Min Act: -0.1700
Data Index: 8809490 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4825. Min Range: -7.4825
Max Act: 7.2950. Min Act: -0.1700
Data Index: 5890714 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4825. Min Range: -7.4825
Max Act: 7.1700. Min Act: -0.1700
Data Index: 4710955 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4825. Min Range: -7.4825
Max Act: 7.1700. Min Act: -0.1700
Data Index: 8368467 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4825. Min Range: -7.4825
Max Act: 7.1075. Min Act: -0.1700
Data Index: 3121361 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4825. Min Range: -7.4825
Max Act: 7.0450. Min Act: -0.1700
Data Index: 6361065 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.9825. Min Act: -0.1700
Data Index: 8559199 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.9825. Min Act: -0.1700
Data Index: 7634656 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.9200. Min Act: -0.1700
Data Index: 5013988 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.8887. Min Act: -0.1700
Data Index: 3616299 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.8887. Min Act: -0.1700
Data Index: 3501524 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.9200. Min Act: -0.1700
Data Index: 7118499 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.8887. Min Act: -0.1700
Data Index: 8827501 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.8575. Min Act: -0.1700
Data Index: 7628691 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.8262. Min Act: -0.1700
Data Index: 5077791 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.8575. Min Act: -0.1700
Data Index: 859456 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.7950. Min Act: -0.1700
Data Index: 8573550 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.8262. Min Act: -0.1700
Data Index: 7771621 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.7950. Min Act: -0.1700
Data Index: 1326906 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19