Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.7389. Min Act: -0.1700
Data Index: 6754018 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.7076. Min Act: -0.1700
Data Index: 515532 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.5514. Min Act: -0.1700
Data Index: 8238432 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.5514. Min Act: -0.1700
Data Index: 2062038 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.5514. Min Act: -0.1700
Data Index: 3979588 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.5514. Min Act: -0.1700
Data Index: 4928357 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.5514. Min Act: -0.1700
Data Index: 6213645 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.5201. Min Act: -0.1700
Data Index: 6183912 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.4889. Min Act: -0.1700
Data Index: 2562214 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.4889. Min Act: -0.1700
Data Index: 1141750 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.4889. Min Act: -0.1700
Data Index: 1738667 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.4576. Min Act: -0.1699
Data Index: 4082303 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.4576. Min Act: -0.1698
Data Index: 1391724 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.4889. Min Act: -0.1700
Data Index: 1065524 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.4264. Min Act: -0.1700
Data Index: 927480 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.4264. Min Act: -0.1700
Data Index: 6906736 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.4264. Min Act: -0.1700
Data Index: 3578988 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.4264. Min Act: -0.1698
Data Index: 4552571 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.4264. Min Act: -0.1700
Data Index: 6695385 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7389. Min Range: -4.7389
Max Act: 4.4264. Min Act: -0.1700
Data Index: 3708161 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19