Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2187 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.5104. Min Act: -0.1700
Data Index: 2712973 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.3854. Min Act: -0.1700
Data Index: 926333 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1979. Min Act: -0.1700
Data Index: 1203686 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1979. Min Act: -0.1700
Data Index: 7531467 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1979. Min Act: -0.1700
Data Index: 8744880 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.2292. Min Act: -0.1700
Data Index: 5564753 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1979. Min Act: -0.1700
Data Index: 3458824 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1667. Min Act: -0.1700
Data Index: 8189925 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1354. Min Act: -0.1700
Data Index: 3872355 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1042. Min Act: -0.1700
Data Index: 2854853 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1354. Min Act: -0.1700
Data Index: 3780829 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1354. Min Act: -0.1700
Data Index: 5714081 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1042. Min Act: -0.1700
Data Index: 5590744 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1042. Min Act: -0.1700
Data Index: 5473638 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.0729. Min Act: -0.1700
Data Index: 1463069 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1042. Min Act: -0.1700
Data Index: 382773 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.0729. Min Act: -0.1700
Data Index: 3593804 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.1042. Min Act: -0.1700
Data Index: 6813716 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.0729. Min Act: -0.1700
Data Index: 8074411 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5104. Min Range: -5.5104
Max Act: 5.0729. Min Act: -0.1700
Data Index: 167420 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19