Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2861 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3676. Min Range: -8.3676
Max Act: 8.3676. Min Act: -0.1700
Data Index: 4419081 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3676. Min Range: -8.3676
Max Act: 8.1801. Min Act: -0.1700
Data Index: 6016969 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3676. Min Range: -8.3676
Max Act: 8.1176. Min Act: -0.1700
Data Index: 2254958 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3676. Min Range: -8.3676
Max Act: 8.0239. Min Act: -0.1700
Data Index: 6171322 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.9301. Min Act: -0.1700
Data Index: 1015463 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.9301. Min Act: -0.1700
Data Index: 1068031 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.9301. Min Act: -0.1700
Data Index: 4138793 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8989. Min Act: -0.1700
Data Index: 3538195 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8676. Min Act: -0.1700
Data Index: 1480773 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8676. Min Act: -0.1700
Data Index: 3658509 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8364. Min Act: -0.1700
Data Index: 2816927 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8364. Min Act: -0.1700
Data Index: 4199257 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8676. Min Act: -0.1700
Data Index: 6430746 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8051. Min Act: -0.1700
Data Index: 2751452 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8051. Min Act: -0.1700
Data Index: 6542760 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8051. Min Act: -0.1700
Data Index: 2325889 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8051. Min Act: -0.1700
Data Index: 7982765 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8051. Min Act: -0.1700
Data Index: 2010369 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8051. Min Act: -0.1700
Data Index: 2465598 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3676. Min Range: -8.3676
Max Act: 7.8051. Min Act: -0.1700
Data Index: 4297206 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19