Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1289 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.5365. Min Act: -0.1700
Data Index: 955427 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.5365. Min Act: -0.1700
Data Index: 5939807 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.5365. Min Act: -0.1700
Data Index: 5912428 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.5365. Min Act: -0.1700
Data Index: 4181602 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.4740. Min Act: -0.1700
Data Index: 4612655 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.4428. Min Act: -0.1700
Data Index: 4535009 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.4115. Min Act: -0.1700
Data Index: 856914 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.4115. Min Act: -0.1700
Data Index: 5346069 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.4115. Min Act: -0.1700
Data Index: 2744462 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.4115. Min Act: -0.1700
Data Index: 5304865 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.4115. Min Act: -0.1700
Data Index: 6033123 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.4428. Min Act: -0.1700
Data Index: 2371911 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.4115. Min Act: -0.1700
Data Index: 1671865 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.3490. Min Act: -0.1700
Data Index: 7952441 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.3803. Min Act: -0.1700
Data Index: 5287989 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.3178. Min Act: -0.1700
Data Index: 2880916 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.3490. Min Act: -0.1700
Data Index: 3004439 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.3490. Min Act: -0.1700
Data Index: 4369655 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.3490. Min Act: -0.1700
Data Index: 6298607 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.3803. Min Act: -0.1700
Data Index: 6987837 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19