Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 847 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1429. Min Range: -3.1429
Max Act: 3.1429. Min Act: -0.1700
Data Index: 8781675 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1429. Min Range: -3.1429
Max Act: 3.0168. Min Act: -0.1700
Data Index: 6560114 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1429. Min Range: -3.1429
Max Act: 3.0010. Min Act: -0.1700
Data Index: 787772 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1429. Min Range: -3.1429
Max Act: 3.0326. Min Act: -0.1700
Data Index: 4692855 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9694. Min Act: -0.1700
Data Index: 164880 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9852. Min Act: -0.1700
Data Index: 49694 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9694. Min Act: -0.1700
Data Index: 3055344 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9535. Min Act: -0.1700
Data Index: 2827349 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9535. Min Act: -0.1700
Data Index: 6284964 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9377. Min Act: -0.1700
Data Index: 2658256 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9377. Min Act: -0.1700
Data Index: 8291685 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9377. Min Act: -0.1700
Data Index: 8556122 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9219. Min Act: -0.1700
Data Index: 1979244 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9060. Min Act: -0.1700
Data Index: 7765805 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9219. Min Act: -0.1700
Data Index: 1168799 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9060. Min Act: -0.1700
Data Index: 1787586 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9060. Min Act: -0.1700
Data Index: 7830752 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9060. Min Act: -0.1700
Data Index: 7572992 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.9219. Min Act: -0.1700
Data Index: 5794348 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1429. Min Range: -3.1429
Max Act: 2.8901. Min Act: -0.1700
Data Index: 111980 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19