Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3776 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.4527. Min Act: -0.1700
Data Index: 1838636 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2652. Min Act: -0.1700
Data Index: 4336246 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2965. Min Act: -0.1700
Data Index: 4848758 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2965. Min Act: -0.1700
Data Index: 1203487 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2340. Min Act: -0.1700
Data Index: 1217382 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2340. Min Act: -0.1700
Data Index: 2373801 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2340. Min Act: -0.1700
Data Index: 1834151 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2340. Min Act: -0.1700
Data Index: 8812864 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2340. Min Act: -0.1700
Data Index: 2856831 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2027. Min Act: -0.1700
Data Index: 4180650 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2027. Min Act: -0.1700
Data Index: 5068094 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2027. Min Act: -0.1700
Data Index: 1312508 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2027. Min Act: -0.1700
Data Index: 2725607 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2027. Min Act: -0.1700
Data Index: 309431 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.1715. Min Act: -0.1700
Data Index: 395268 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2027. Min Act: -0.1700
Data Index: 1840390 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.1715. Min Act: -0.1700
Data Index: 1321159 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.1715. Min Act: -0.1700
Data Index: 7453742 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.1402. Min Act: -0.1700
Data Index: 2621999 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4527. Min Range: -5.4527
Max Act: 5.2027. Min Act: -0.1700
Data Index: 7577190 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19