Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4070 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.3410. Min Act: -0.1700
Data Index: 7407061 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.3253. Min Act: -0.1700
Data Index: 5339930 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.3096. Min Act: -0.1700
Data Index: 8224690 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2311. Min Act: -0.1700
Data Index: 1000483 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1997. Min Act: -0.1700
Data Index: 1634042 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1682. Min Act: -0.1700
Data Index: 6245424 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1839. Min Act: -0.1700
Data Index: 2021161 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1525. Min Act: -0.1700
Data Index: 999387 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1682. Min Act: -0.1700
Data Index: 1037979 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1525. Min Act: -0.1700
Data Index: 3575806 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1367. Min Act: -0.1700
Data Index: 8531359 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1052. Min Act: -0.1700
Data Index: 1916317 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0737. Min Act: -0.1700
Data Index: 7329366 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0895. Min Act: -0.1700
Data Index: 1283714 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0895. Min Act: -0.1700
Data Index: 2453617 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0895. Min Act: -0.1700
Data Index: 8714801 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0895. Min Act: -0.1700
Data Index: 711120 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0737. Min Act: -0.1700
Data Index: 5868989 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0579. Min Act: -0.1700
Data Index: 1750174 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0579. Min Act: -0.1700
Data Index: 6569889 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19