Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2755 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.7031. Min Act: -0.1700
Data Index: 4163821 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6868. Min Act: -0.1700
Data Index: 3174902 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6706. Min Act: -0.1700
Data Index: 3727021 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6706. Min Act: -0.1700
Data Index: 461838 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6545. Min Act: -0.1700
Data Index: 2942330 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6706. Min Act: -0.1700
Data Index: 3775288 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6545. Min Act: -0.1700
Data Index: 4631617 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6384. Min Act: -0.1700
Data Index: 5254896 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6225. Min Act: -0.1700
Data Index: 6755544 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6384. Min Act: -0.1700
Data Index: 1403992 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6225. Min Act: -0.1695
Data Index: 8512545 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6225. Min Act: -0.1700
Data Index: 8352222 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6225. Min Act: -0.1700
Data Index: 3078490 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6067. Min Act: -0.1700
Data Index: 2809938 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.5909. Min Act: -0.1700
Data Index: 286938 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6067. Min Act: -0.1691
Data Index: 3217794 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6067. Min Act: -0.1700
Data Index: 2873844 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6067. Min Act: -0.1700
Data Index: 5507033 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6067. Min Act: -0.1700
Data Index: 1232833 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7031. Min Range: -0.7031
Max Act: 0.6067. Min Act: -0.1700
Data Index: 4512707 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19