Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4071 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2771. Min Range: -4.2771
Max Act: 4.2771. Min Act: -0.1700
Data Index: 1312120 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2771. Min Range: -4.2771
Max Act: 4.1209. Min Act: -0.1700
Data Index: 7354129 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2771. Min Range: -4.2771
Max Act: 4.0896. Min Act: -0.1700
Data Index: 4877799 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2771. Min Range: -4.2771
Max Act: 4.0896. Min Act: -0.1700
Data Index: 4172662 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2771. Min Range: -4.2771
Max Act: 4.0584. Min Act: -0.1700
Data Index: 5714749 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2771. Min Range: -4.2771
Max Act: 4.0271. Min Act: -0.1700
Data Index: 6139245 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.9958. Min Act: -0.1700
Data Index: 3465445 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.9333. Min Act: -0.1700
Data Index: 7205789 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.9646. Min Act: -0.1700
Data Index: 7648224 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.9646. Min Act: -0.1700
Data Index: 8814239 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.9646. Min Act: -0.1700
Data Index: 4356227 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.9020. Min Act: -0.1700
Data Index: 7182949 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.9333. Min Act: -0.1700
Data Index: 2106589 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.9020. Min Act: -0.1700
Data Index: 7141978 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.9333. Min Act: -0.1700
Data Index: 7744574 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.8708. Min Act: -0.1700
Data Index: 6837873 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.9020. Min Act: -0.1700
Data Index: 7242427 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.9020. Min Act: -0.1700
Data Index: 6006524 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.8708. Min Act: -0.1700
Data Index: 6660506 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2771. Min Range: -4.2771
Max Act: 3.8708. Min Act: -0.1700
Data Index: 1178288 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19