Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2428 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2357. Min Range: -5.2357
Max Act: 5.2357. Min Act: -0.1700
Data Index: 6902559 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2357. Min Range: -5.2357
Max Act: 5.1419. Min Act: -0.1700
Data Index: 2962907 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2357. Min Range: -5.2357
Max Act: 5.0482. Min Act: -0.1700
Data Index: 5401364 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.9857. Min Act: -0.1700
Data Index: 7137237 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.9232. Min Act: -0.1700
Data Index: 6637274 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.8294. Min Act: -0.1700
Data Index: 6659181 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.8294. Min Act: -0.1700
Data Index: 290290 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.8294. Min Act: -0.1700
Data Index: 1905628 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.7982. Min Act: -0.1700
Data Index: 4270182 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.8294. Min Act: -0.1700
Data Index: 7402746 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.7982. Min Act: -0.1700
Data Index: 2675184 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.7669. Min Act: -0.1700
Data Index: 332344 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.7669. Min Act: -0.1700
Data Index: 5607409 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.7669. Min Act: -0.1700
Data Index: 3107004 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.7669. Min Act: -0.1700
Data Index: 7446330 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.7357. Min Act: -0.1700
Data Index: 4732434 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.7357. Min Act: -0.1700
Data Index: 5324758 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.7357. Min Act: -0.1700
Data Index: 1525017 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.7044. Min Act: -0.1700
Data Index: 564071 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2357. Min Range: -5.2357
Max Act: 4.7357. Min Act: -0.1700
Data Index: 4167733 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19