Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.5202. Min Act: -0.1700
Data Index: 7274876 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.3478. Min Act: -0.1700
Data Index: 3279547 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.2850. Min Act: -0.1700
Data Index: 6770612 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.2693. Min Act: -0.1700
Data Index: 2587323 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.2536. Min Act: -0.1700
Data Index: 6837816 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.2221. Min Act: -0.1700
Data Index: 1102492 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.2221. Min Act: -0.1700
Data Index: 3950989 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1750. Min Act: -0.1700
Data Index: 8053345 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1907. Min Act: -0.1700
Data Index: 831907 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1750. Min Act: -0.1700
Data Index: 4466880 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1750. Min Act: -0.1700
Data Index: 8471814 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1750. Min Act: -0.1700
Data Index: 2785267 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1592. Min Act: -0.1700
Data Index: 5674550 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1592. Min Act: -0.1700
Data Index: 2037028 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1277. Min Act: -0.1700
Data Index: 689995 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1435. Min Act: -0.1700
Data Index: 6649708 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1435. Min Act: -0.1700
Data Index: 6613641 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1277. Min Act: -0.1700
Data Index: 2570904 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1277. Min Act: -0.1700
Data Index: 8567173 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5202. Min Range: -3.5202
Max Act: 3.1277. Min Act: -0.1700
Data Index: 3557510 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19