Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3299 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1706. Min Range: -6.1706
Max Act: 6.1706. Min Act: -0.1700
Data Index: 7543843 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1706. Min Range: -6.1706
Max Act: 6.1394. Min Act: -0.1700
Data Index: 4295696 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1706. Min Range: -6.1706
Max Act: 6.1081. Min Act: -0.1700
Data Index: 6066862 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1706. Min Range: -6.1706
Max Act: 6.1081. Min Act: -0.1700
Data Index: 6454044 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1706. Min Range: -6.1706
Max Act: 6.0456. Min Act: -0.1700
Data Index: 1441581 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1706. Min Range: -6.1706
Max Act: 6.0769. Min Act: -0.1700
Data Index: 806393 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1706. Min Range: -6.1706
Max Act: 6.0456. Min Act: -0.1700
Data Index: 4450322 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1706. Min Range: -6.1706
Max Act: 6.0456. Min Act: -0.1700
Data Index: 946374 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1706. Min Range: -6.1706
Max Act: 6.0144. Min Act: -0.1700
Data Index: 5950696 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1706. Min Range: -6.1706
Max Act: 6.0144. Min Act: -0.1700
Data Index: 5971260 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1706. Min Range: -6.1706
Max Act: 6.0144. Min Act: -0.1700
Data Index: 596599 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1706. Min Range: -6.1706
Max Act: 5.9519. Min Act: -0.1700
Data Index: 339260 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1706. Min Range: -6.1706
Max Act: 5.9206. Min Act: -0.1700
Data Index: 215304 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1706. Min Range: -6.1706
Max Act: 5.8894. Min Act: -0.1700
Data Index: 1722767 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1706. Min Range: -6.1706
Max Act: 5.8581. Min Act: -0.1700
Data Index: 4541453 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1706. Min Range: -6.1706
Max Act: 5.8894. Min Act: -0.1700
Data Index: 5111757 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1706. Min Range: -6.1706
Max Act: 5.8581. Min Act: -0.1700
Data Index: 6542691 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1706. Min Range: -6.1706
Max Act: 5.8581. Min Act: -0.1700
Data Index: 2049496 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1706. Min Range: -6.1706
Max Act: 5.8581. Min Act: -0.1700
Data Index: 8128374 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1706. Min Range: -6.1706
Max Act: 5.8581. Min Act: -0.1700
Data Index: 7368388 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19