Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4668 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0300. Min Range: -7.0300
Max Act: 7.0300. Min Act: -0.1700
Data Index: 8671441 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.9675. Min Act: -0.1700
Data Index: 7352928 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.9050. Min Act: -0.1700
Data Index: 3678207 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.8738. Min Act: -0.1700
Data Index: 8591571 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.7488. Min Act: -0.1700
Data Index: 7501716 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.6863. Min Act: -0.1700
Data Index: 2421421 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.6550. Min Act: -0.1700
Data Index: 5376449 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.6863. Min Act: -0.1700
Data Index: 5063213 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.6238. Min Act: -0.1700
Data Index: 3180715 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.6238. Min Act: -0.1700
Data Index: 6231551 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.6238. Min Act: -0.1700
Data Index: 7978418 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.6550. Min Act: -0.1700
Data Index: 7979810 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.6238. Min Act: -0.1700
Data Index: 2282461 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.5925. Min Act: -0.1700
Data Index: 2909849 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.5925. Min Act: -0.1700
Data Index: 3322192 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.5613. Min Act: -0.1700
Data Index: 7153061 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.5613. Min Act: -0.1700
Data Index: 3282624 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.5300. Min Act: -0.1700
Data Index: 5957200 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.5300. Min Act: -0.1700
Data Index: 1174294 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0300. Min Range: -7.0300
Max Act: 6.4675. Min Act: -0.1700
Data Index: 1827531 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19