Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2170. Min Range: -6.2170
Max Act: 6.2170. Min Act: -0.1700
Data Index: 4529482 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2170. Min Range: -6.2170
Max Act: 6.1858. Min Act: -0.1700
Data Index: 961022 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2170. Min Range: -6.2170
Max Act: 6.1233. Min Act: -0.1700
Data Index: 7039282 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2170. Min Range: -6.2170
Max Act: 6.0295. Min Act: -0.1700
Data Index: 4000256 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2170. Min Range: -6.2170
Max Act: 6.0608. Min Act: -0.1700
Data Index: 8024520 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.9983. Min Act: -0.1700
Data Index: 602867 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.9983. Min Act: -0.1700
Data Index: 3546308 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.9670. Min Act: -0.1700
Data Index: 6862852 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.9358. Min Act: -0.1700
Data Index: 6188251 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.9358. Min Act: -0.1700
Data Index: 7733309 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.9045. Min Act: -0.1700
Data Index: 6900840 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.8420. Min Act: -0.1700
Data Index: 5178299 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.8420. Min Act: -0.1700
Data Index: 117155 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.8420. Min Act: -0.1700
Data Index: 3364838 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.8420. Min Act: -0.1700
Data Index: 1783812 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.8420. Min Act: -0.1700
Data Index: 3125404 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.8108. Min Act: -0.1700
Data Index: 6564552 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.8733. Min Act: -0.1700
Data Index: 6386600 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.8108. Min Act: -0.1700
Data Index: 7029979 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2170. Min Range: -6.2170
Max Act: 5.8108. Min Act: -0.1700
Data Index: 6288279 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19