Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6000 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.6017. Min Act: -0.1700
Data Index: 6539426 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.5704. Min Act: -0.1700
Data Index: 1675777 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.5704. Min Act: -0.1700
Data Index: 2472922 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.5079. Min Act: -0.1700
Data Index: 6587509 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.5704. Min Act: -0.1700
Data Index: 2779954 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.5079. Min Act: -0.1700
Data Index: 6271510 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.5079. Min Act: -0.1700
Data Index: 4759357 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.5079. Min Act: -0.1700
Data Index: 3427672 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.5079. Min Act: -0.1700
Data Index: 3853259 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.5079. Min Act: -0.1700
Data Index: 3351291 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.5392. Min Act: -0.1700
Data Index: 8002733 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.4454. Min Act: -0.1700
Data Index: 3411075 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.4767. Min Act: -0.1700
Data Index: 7838212 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.4454. Min Act: -0.1700
Data Index: 273039 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.4454. Min Act: -0.1700
Data Index: 2698461 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.4454. Min Act: -0.1700
Data Index: 7129825 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.4454. Min Act: -0.1700
Data Index: 2571813 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.4142. Min Act: -0.1700
Data Index: 7050339 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.4142. Min Act: -0.1700
Data Index: 8024917 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6017. Min Range: -5.6017
Max Act: 5.4142. Min Act: -0.1700
Data Index: 1798790 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19