Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1407 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.8269. Min Act: -0.1700
Data Index: 1960099 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.6394. Min Act: -0.1700
Data Index: 8044485 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.5144. Min Act: -0.1699
Data Index: 2077295 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.4519. Min Act: -0.1700
Data Index: 5180060 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.3894. Min Act: -0.1700
Data Index: 1210333 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.2644. Min Act: -0.1700
Data Index: 7181933 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.3269. Min Act: -0.1700
Data Index: 4850310 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.2644. Min Act: -0.1700
Data Index: 8152574 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.2644. Min Act: -0.1699
Data Index: 3938024 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.2019. Min Act: -0.1700
Data Index: 6020123 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.1394. Min Act: -0.1700
Data Index: 6418405 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.0769. Min Act: -0.1700
Data Index: 2669898 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.0769. Min Act: -0.1700
Data Index: 341586 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.0769. Min Act: -0.1699
Data Index: 523850 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.0769. Min Act: -0.1700
Data Index: 8622018 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.0769. Min Act: -0.1700
Data Index: 5743122 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.0769. Min Act: -0.1700
Data Index: 4418932 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8269. Min Range: -9.8269
Max Act: 9.1394. Min Act: -0.1700
Data Index: 382120 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8269. Min Range: -9.8269
Max Act: 8.9519. Min Act: -0.1700
Data Index: 7914133 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8269. Min Range: -9.8269
Max Act: 8.9519. Min Act: -0.1700
Data Index: 2527142 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19