Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2238 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0001. Min Range: -2.0001
Max Act: 2.0001. Min Act: -0.1700
Data Index: 613680 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0001. Min Range: -2.0001
Max Act: 2.0001. Min Act: -0.1700
Data Index: 8779061 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9832. Min Act: -0.1700
Data Index: 4388901 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9832. Min Act: -0.1700
Data Index: 5449200 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0001. Min Range: -2.0001
Max Act: 2.0001. Min Act: -0.1700
Data Index: 3273935 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9662. Min Act: -0.1700
Data Index: 280848 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9832. Min Act: -0.1700
Data Index: 1839953 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9662. Min Act: -0.1700
Data Index: 1818633 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9662. Min Act: -0.1700
Data Index: 3303729 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9662. Min Act: -0.1700
Data Index: 8788782 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9662. Min Act: -0.1700
Data Index: 3991025 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9662. Min Act: -0.1700
Data Index: 6389095 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9662. Min Act: -0.1700
Data Index: 6587609 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9492. Min Act: -0.1700
Data Index: 6391790 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9323. Min Act: -0.1700
Data Index: 5824834 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9492. Min Act: -0.1700
Data Index: 241499 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9323. Min Act: -0.1699
Data Index: 7374802 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9323. Min Act: -0.1700
Data Index: 6588824 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9323. Min Act: -0.1700
Data Index: 218080 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0001. Min Range: -2.0001
Max Act: 1.9323. Min Act: -0.1700
Data Index: 4502460 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19