Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1649 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3799. Min Range: -8.3799
Max Act: 8.3799. Min Act: -0.1700
Data Index: 6270547 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3799. Min Range: -8.3799
Max Act: 8.2549. Min Act: -0.1700
Data Index: 5228955 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3799. Min Range: -8.3799
Max Act: 8.1924. Min Act: -0.1700
Data Index: 4147094 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3799. Min Range: -8.3799
Max Act: 8.0674. Min Act: -0.1700
Data Index: 5368516 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3799. Min Range: -8.3799
Max Act: 8.0674. Min Act: -0.1700
Data Index: 3127294 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.9424. Min Act: -0.1700
Data Index: 6087271 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.9736. Min Act: -0.1700
Data Index: 5108686 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.9424. Min Act: -0.1700
Data Index: 3278988 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.9424. Min Act: -0.1700
Data Index: 2402273 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.8174. Min Act: -0.1700
Data Index: 4161704 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.7549. Min Act: -0.1700
Data Index: 1505080 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.7236. Min Act: -0.1700
Data Index: 6696629 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.7236. Min Act: -0.1700
Data Index: 2619440 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.7236. Min Act: -0.1700
Data Index: 4385096 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.6924. Min Act: -0.1700
Data Index: 3630463 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.6924. Min Act: -0.1700
Data Index: 1744545 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.6611. Min Act: -0.1700
Data Index: 7645891 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.6611. Min Act: -0.1700
Data Index: 4719011 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.6611. Min Act: -0.1700
Data Index: 7980248 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3799. Min Range: -8.3799
Max Act: 7.6611. Min Act: -0.1700
Data Index: 2657484 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19