Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3115 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.9852. Min Act: -0.1700
Data Index: 1777581 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.9694. Min Act: -0.1700
Data Index: 1570836 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.9536. Min Act: -0.1700
Data Index: 6396259 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.9061. Min Act: -0.1700
Data Index: 4874616 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.8743. Min Act: -0.1700
Data Index: 8199328 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.9061. Min Act: -0.1700
Data Index: 6709705 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.8426. Min Act: -0.1700
Data Index: 5677614 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.8426. Min Act: -0.1700
Data Index: 4763312 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.8267. Min Act: -0.1700
Data Index: 1896294 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.8426. Min Act: -0.1700
Data Index: 993565 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.8108. Min Act: -0.1700
Data Index: 6856309 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.8267. Min Act: -0.1700
Data Index: 5677615 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.7948. Min Act: -0.1700
Data Index: 5572920 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.8108. Min Act: -0.1700
Data Index: 1073785 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.8108. Min Act: -0.1700
Data Index: 2642242 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.7789. Min Act: -0.1700
Data Index: 6158713 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.7789. Min Act: -0.1700
Data Index: 6878085 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.7948. Min Act: -0.1700
Data Index: 6960159 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.7470. Min Act: -0.1700
Data Index: 2202365 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9852. Min Range: -2.9852
Max Act: 2.7789. Min Act: -0.1700
Data Index: 4188252 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19