Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1892 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.4611. Min Act: -0.1700
Data Index: 1135073 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.4122. Min Act: -0.1700
Data Index: 7531066 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.4285. Min Act: -0.1700
Data Index: 549219 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.3959. Min Act: -0.1700
Data Index: 6006741 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.3469. Min Act: -0.1700
Data Index: 4176849 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.3469. Min Act: -0.1700
Data Index: 5512664 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.3305. Min Act: -0.1700
Data Index: 7637643 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.3469. Min Act: -0.1700
Data Index: 6300551 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.3469. Min Act: -0.1700
Data Index: 8121468 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.3140. Min Act: -0.1700
Data Index: 280496 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.3140. Min Act: -0.1700
Data Index: 7040085 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.2976. Min Act: -0.1700
Data Index: 4553310 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.2976. Min Act: -0.1700
Data Index: 3933085 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.2811. Min Act: -0.1700
Data Index: 7294084 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.2811. Min Act: -0.1700
Data Index: 975318 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.2811. Min Act: -0.1700
Data Index: 2299891 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.2976. Min Act: -0.1700
Data Index: 8357407 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.2646. Min Act: -0.1700
Data Index: 1322648 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.2646. Min Act: -0.1700
Data Index: 5951464 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4611. Min Range: -2.4611
Max Act: 2.2481. Min Act: -0.1700
Data Index: 5069700 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19