Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6369 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3804. Min Range: -9.3804
Max Act: 9.3804. Min Act: -0.1700
Data Index: 1076786 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3804. Min Range: -9.3804
Max Act: 9.2554. Min Act: -0.1700
Data Index: 7600587 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3804. Min Range: -9.3804
Max Act: 9.2554. Min Act: -0.1700
Data Index: 1909236 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3804. Min Range: -9.3804
Max Act: 9.1304. Min Act: -0.1700
Data Index: 6868787 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3804. Min Range: -9.3804
Max Act: 9.1304. Min Act: -0.1700
Data Index: 2325408 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3804. Min Range: -9.3804
Max Act: 9.1929. Min Act: -0.1700
Data Index: 5601571 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3804. Min Range: -9.3804
Max Act: 9.1304. Min Act: -0.1700
Data Index: 5869632 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3804. Min Range: -9.3804
Max Act: 9.0679. Min Act: -0.1700
Data Index: 7843515 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3804. Min Range: -9.3804
Max Act: 9.0054. Min Act: -0.1700
Data Index: 6609292 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3804. Min Range: -9.3804
Max Act: 9.0054. Min Act: -0.1700
Data Index: 7874695 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3804. Min Range: -9.3804
Max Act: 8.9429. Min Act: -0.1700
Data Index: 4340347 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3804. Min Range: -9.3804
Max Act: 8.9429. Min Act: -0.1700
Data Index: 2034047 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3804. Min Range: -9.3804
Max Act: 8.9429. Min Act: -0.1700
Data Index: 78391 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3804. Min Range: -9.3804
Max Act: 8.9429. Min Act: -0.1700
Data Index: 3966672 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3804. Min Range: -9.3804
Max Act: 8.9429. Min Act: -0.1700
Data Index: 3225381 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3804. Min Range: -9.3804
Max Act: 8.8804. Min Act: -0.1700
Data Index: 1050947 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3804. Min Range: -9.3804
Max Act: 8.8179. Min Act: -0.1700
Data Index: 2972647 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3804. Min Range: -9.3804
Max Act: 8.8804. Min Act: -0.1700
Data Index: 2125209 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3804. Min Range: -9.3804
Max Act: 8.8179. Min Act: -0.1700
Data Index: 1649475 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3804. Min Range: -9.3804
Max Act: 8.8179. Min Act: -0.1700
Data Index: 3334140 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19