Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2200 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5447. Min Range: -6.5447
Max Act: 6.5447. Min Act: -0.1700
Data Index: 4669130 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5447. Min Range: -6.5447
Max Act: 6.2322. Min Act: -0.1700
Data Index: 8814338 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5447. Min Range: -6.5447
Max Act: 6.1697. Min Act: -0.1700
Data Index: 1731646 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5447. Min Range: -6.5447
Max Act: 6.1072. Min Act: -0.1700
Data Index: 253066 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5447. Min Range: -6.5447
Max Act: 6.0134. Min Act: -0.1700
Data Index: 1658152 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.9822. Min Act: -0.1700
Data Index: 8761332 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.9822. Min Act: -0.1700
Data Index: 5380318 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5447. Min Range: -6.5447
Max Act: 6.0134. Min Act: -0.1700
Data Index: 8065152 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.9509. Min Act: -0.1700
Data Index: 701048 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.9197. Min Act: -0.1700
Data Index: 2751545 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.8884. Min Act: -0.1700
Data Index: 7768468 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.8884. Min Act: -0.1700
Data Index: 6328059 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.8884. Min Act: -0.1700
Data Index: 7927150 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.8572. Min Act: -0.1700
Data Index: 6042683 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.8259. Min Act: -0.1700
Data Index: 8263245 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.8572. Min Act: -0.1700
Data Index: 3954446 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.8572. Min Act: -0.1700
Data Index: 2855938 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.7634. Min Act: -0.1700
Data Index: 7656835 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.7947. Min Act: -0.1700
Data Index: 4142338 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5447. Min Range: -6.5447
Max Act: 5.7634. Min Act: -0.1700
Data Index: 1909065 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19