Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2126 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2372. Min Range: -5.2372
Max Act: 5.2372. Min Act: -0.1700
Data Index: 6488124 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2372. Min Range: -5.2372
Max Act: 5.2372. Min Act: -0.1700
Data Index: 7144901 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2372. Min Range: -5.2372
Max Act: 5.1747. Min Act: -0.1700
Data Index: 745761 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2372. Min Range: -5.2372
Max Act: 5.1747. Min Act: -0.1700
Data Index: 6488125 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2372. Min Range: -5.2372
Max Act: 5.0184. Min Act: -0.1700
Data Index: 2149665 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2372. Min Range: -5.2372
Max Act: 5.0184. Min Act: -0.1700
Data Index: 8283099 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.9872. Min Act: -0.1700
Data Index: 6488123 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.9559. Min Act: -0.1700
Data Index: 1048802 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.9247. Min Act: -0.1700
Data Index: 3555111 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.8934. Min Act: -0.1700
Data Index: 1792440 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.8934. Min Act: -0.1700
Data Index: 1792439 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.8934. Min Act: -0.1700
Data Index: 303757 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.8934. Min Act: -0.1700
Data Index: 747738 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.8622. Min Act: -0.1700
Data Index: 6488126 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.8622. Min Act: -0.1700
Data Index: 3555115 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.7997. Min Act: -0.1700
Data Index: 4369275 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.8309. Min Act: -0.1697
Data Index: 1313697 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.8622. Min Act: -0.1700
Data Index: 3872915 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.7997. Min Act: -0.1700
Data Index: 6853558 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2372. Min Range: -5.2372
Max Act: 4.7997. Min Act: -0.1700
Data Index: 4260464 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19