Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4266 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.6860. Min Act: -0.1700
Data Index: 4178868 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.6548. Min Act: -0.1700
Data Index: 7544098 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.6235. Min Act: -0.1700
Data Index: 1610178 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.5610. Min Act: -0.1700
Data Index: 6514921 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.4673. Min Act: -0.1700
Data Index: 5912168 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.4360. Min Act: -0.1700
Data Index: 6708874 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.4048. Min Act: -0.1700
Data Index: 3878724 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.4048. Min Act: -0.1700
Data Index: 1668487 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.3735. Min Act: -0.1700
Data Index: 3960423 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.3423. Min Act: -0.1700
Data Index: 7157137 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.3423. Min Act: -0.1700
Data Index: 6851432 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.3110. Min Act: -0.1700
Data Index: 8122520 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.3110. Min Act: -0.1700
Data Index: 7855644 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.3110. Min Act: -0.1700
Data Index: 1803156 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.3110. Min Act: -0.1700
Data Index: 5689915 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.3110. Min Act: -0.1700
Data Index: 2444449 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.3110. Min Act: -0.1700
Data Index: 5506166 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.3110. Min Act: -0.1700
Data Index: 1405667 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.2798. Min Act: -0.1700
Data Index: 4583941 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6860. Min Range: -5.6860
Max Act: 5.2798. Min Act: -0.1700
Data Index: 1980112 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19