Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 691 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.7954. Min Act: -0.1681
Data Index: 3848816 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.7289. Min Act: -0.1700
Data Index: 1107245 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.7289. Min Act: -0.1700
Data Index: 110496 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.7289. Min Act: -0.1697
Data Index: 2476080 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6880. Min Act: -0.1698
Data Index: 8785626 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6718. Min Act: -0.1691
Data Index: 785632 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6718. Min Act: -0.1700
Data Index: 8012918 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6397. Min Act: -0.1425
Data Index: 6830584 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6317. Min Act: -0.1694
Data Index: 975860 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6397. Min Act: -0.1699
Data Index: 5201140 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6397. Min Act: -0.1664
Data Index: 5304883 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6397. Min Act: -0.1697
Data Index: 1544692 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6317. Min Act: -0.1699
Data Index: 3748941 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6237. Min Act: -0.1700
Data Index: 6860212 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6317. Min Act: -0.1695
Data Index: 7729331 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6237. Min Act: -0.1677
Data Index: 7826338 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6158. Min Act: -0.1536
Data Index: 6132352 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6079. Min Act: -0.1686
Data Index: 1973243 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6079. Min Act: -0.1522
Data Index: 6132344 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7954. Min Range: -0.7954
Max Act: 0.6000. Min Act: -0.1691
Data Index: 4244667 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19