Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1686 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.6679. Min Act: -0.1700
Data Index: 5119000 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.6367. Min Act: -0.1700
Data Index: 4893199 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.5429. Min Act: -0.1700
Data Index: 6518722 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.5117. Min Act: -0.1700
Data Index: 1839943 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.4804. Min Act: -0.1700
Data Index: 4717891 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.4804. Min Act: -0.1700
Data Index: 8426918 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.4492. Min Act: -0.1700
Data Index: 319414 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.4492. Min Act: -0.1700
Data Index: 1537639 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.4492. Min Act: -0.1700
Data Index: 7520737 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.4492. Min Act: -0.1700
Data Index: 5934298 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.4492. Min Act: -0.1700
Data Index: 2368498 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.4179. Min Act: -0.1700
Data Index: 8619350 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.4179. Min Act: -0.1700
Data Index: 5336973 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.3867. Min Act: -0.1700
Data Index: 4523479 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.3867. Min Act: -0.1700
Data Index: 2015681 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.3554. Min Act: -0.1700
Data Index: 4753624 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.3554. Min Act: -0.1700
Data Index: 5784065 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.3242. Min Act: -0.1700
Data Index: 4615989 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.3242. Min Act: -0.1700
Data Index: 3794482 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6679. Min Range: -5.6679
Max Act: 5.3242. Min Act: -0.1700
Data Index: 6838810 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19