Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1880 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.8797. Min Act: -0.1700
Data Index: 8217980 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.8797. Min Act: -0.1700
Data Index: 8730144 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.8540. Min Act: -0.1700
Data Index: 783537 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.8540. Min Act: -0.1700
Data Index: 3973027 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.8369. Min Act: -0.1700
Data Index: 6537671 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.8454. Min Act: -0.1700
Data Index: 4928173 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.8283. Min Act: -0.1700
Data Index: 1729478 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.8283. Min Act: -0.1700
Data Index: 4803967 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.8197. Min Act: -0.1700
Data Index: 5382087 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.8111. Min Act: -0.1700
Data Index: 284034 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.8111. Min Act: -0.1700
Data Index: 8123651 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.8025. Min Act: -0.1700
Data Index: 5654 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.7939. Min Act: -0.1700
Data Index: 406639 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.7939. Min Act: -0.1700
Data Index: 2993040 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.7939. Min Act: -0.1700
Data Index: 4435108 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.7939. Min Act: -0.1700
Data Index: 8090018 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.7939. Min Act: -0.1700
Data Index: 3520641 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.7853. Min Act: -0.1700
Data Index: 1278490 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.7939. Min Act: -0.1700
Data Index: 1449640 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8797. Min Range: -1.8797
Max Act: 1.7939. Min Act: -0.1700
Data Index: 4317935 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19