Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1392 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.3948. Min Act: -0.1700
Data Index: 939896 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.3791. Min Act: -0.1700
Data Index: 5281366 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.3164. Min Act: -0.1700
Data Index: 7639072 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.1907. Min Act: -0.1700
Data Index: 8335823 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.1120. Min Act: -0.1700
Data Index: 4067220 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.1435. Min Act: -0.1700
Data Index: 130157 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.1120. Min Act: -0.1700
Data Index: 2335851 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0962. Min Act: -0.1700
Data Index: 8729300 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0962. Min Act: -0.1700
Data Index: 1604900 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0804. Min Act: -0.1700
Data Index: 7486799 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0962. Min Act: -0.1700
Data Index: 2710506 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0647. Min Act: -0.1700
Data Index: 4221530 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0489. Min Act: -0.1700
Data Index: 124470 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0489. Min Act: -0.1700
Data Index: 1098439 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0804. Min Act: -0.1700
Data Index: 3802672 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0489. Min Act: -0.1700
Data Index: 3756324 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0331. Min Act: -0.1700
Data Index: 655919 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0489. Min Act: -0.1700
Data Index: 1006201 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0173. Min Act: -0.1700
Data Index: 5598320 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3948. Min Range: -3.3948
Max Act: 3.0173. Min Act: -0.1700
Data Index: 1161390 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19