Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2857 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.8789. Min Act: -0.1700
Data Index: 4926417 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.7851. Min Act: -0.1700
Data Index: 1916496 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.4726. Min Act: -0.1700
Data Index: 8407504 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.4726. Min Act: -0.1700
Data Index: 8249191 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.4414. Min Act: -0.1700
Data Index: 7627133 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.4101. Min Act: -0.1700
Data Index: 4473032 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.3476. Min Act: -0.1700
Data Index: 6638380 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.3164. Min Act: -0.1700
Data Index: 6781201 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.3164. Min Act: -0.1700
Data Index: 37503 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.3164. Min Act: -0.1700
Data Index: 6415293 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.2851. Min Act: -0.1700
Data Index: 3763416 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.2226. Min Act: -0.1700
Data Index: 6753813 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.2226. Min Act: -0.1700
Data Index: 4894706 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.2226. Min Act: -0.1700
Data Index: 3525959 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.1914. Min Act: -0.1700
Data Index: 1113331 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.1914. Min Act: -0.1700
Data Index: 8671700 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.1601. Min Act: -0.1700
Data Index: 7125086 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.1601. Min Act: -0.1700
Data Index: 4767467 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.1601. Min Act: -0.1700
Data Index: 8714614 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8789. Min Range: -6.8789
Max Act: 6.1289. Min Act: -0.1700
Data Index: 2397125 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19