Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2216 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1527. Min Range: -6.1527
Max Act: 6.1527. Min Act: -0.1700
Data Index: 5373105 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1527. Min Range: -6.1527
Max Act: 6.0902. Min Act: -0.1700
Data Index: 6823716 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.9652. Min Act: -0.1700
Data Index: 6811329 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.9339. Min Act: -0.1700
Data Index: 8607816 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.9339. Min Act: -0.1700
Data Index: 1718891 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.8714. Min Act: -0.1699
Data Index: 4830803 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.9027. Min Act: -0.1700
Data Index: 1718889 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.8714. Min Act: -0.1700
Data Index: 5778841 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.8714. Min Act: -0.1700
Data Index: 5429527 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.8402. Min Act: -0.1700
Data Index: 6561717 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.8402. Min Act: -0.1700
Data Index: 2371444 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.8402. Min Act: -0.1700
Data Index: 1181080 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.8089. Min Act: -0.1700
Data Index: 2917323 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.7464. Min Act: -0.1700
Data Index: 6342870 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.7152. Min Act: -0.1700
Data Index: 2246623 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.7152. Min Act: -0.1700
Data Index: 8155402 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.7152. Min Act: -0.1700
Data Index: 3568983 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.7152. Min Act: -0.1700
Data Index: 6852250 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.7152. Min Act: -0.1700
Data Index: 5647169 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1527. Min Range: -6.1527
Max Act: 5.6839. Min Act: -0.1700
Data Index: 3227023 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19