Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 763 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.5681. Min Act: -0.1700
Data Index: 6749226 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.4744. Min Act: -0.1700
Data Index: 8135937 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.5056. Min Act: -0.1700
Data Index: 7069035 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.5056. Min Act: -0.1700
Data Index: 7737222 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.4119. Min Act: -0.1700
Data Index: 5459444 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.4431. Min Act: -0.1700
Data Index: 1075946 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.4744. Min Act: -0.1700
Data Index: 6495996 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.3181. Min Act: -0.1700
Data Index: 6878897 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.3494. Min Act: -0.1700
Data Index: 1224006 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.3806. Min Act: -0.1700
Data Index: 4324534 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.3806. Min Act: -0.1700
Data Index: 5021730 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.4119. Min Act: -0.1700
Data Index: 4064702 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.4431. Min Act: -0.1700
Data Index: 7747309 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.3494. Min Act: -0.1700
Data Index: 4104947 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.3806. Min Act: -0.1700
Data Index: 8060752 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.3494. Min Act: -0.1700
Data Index: 3866610 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.2556. Min Act: -0.1700
Data Index: 5258796 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.3181. Min Act: -0.1700
Data Index: 3505682 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.4119. Min Act: -0.1700
Data Index: 5191675 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5681. Min Range: -5.5681
Max Act: 5.3181. Min Act: -0.1700
Data Index: 6537892 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19