Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 889 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.3607. Min Act: -0.1700
Data Index: 8197650 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.0482. Min Act: -0.1700
Data Index: 3604500 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3607. Min Range: -6.3607
Max Act: 6.0170. Min Act: -0.1700
Data Index: 7966310 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.9857. Min Act: -0.1700
Data Index: 905794 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.8920. Min Act: -0.1700
Data Index: 6236599 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.9232. Min Act: -0.1700
Data Index: 3258045 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.8920. Min Act: -0.1700
Data Index: 3498822 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.8607. Min Act: -0.1700
Data Index: 7344990 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.8607. Min Act: -0.1700
Data Index: 2489681 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.8607. Min Act: -0.1700
Data Index: 215851 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.8295. Min Act: -0.1700
Data Index: 6245482 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.7982. Min Act: -0.1700
Data Index: 2041697 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.7670. Min Act: -0.1700
Data Index: 544555 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.7982. Min Act: -0.1700
Data Index: 623118 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.7982. Min Act: -0.1700
Data Index: 8328767 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.7982. Min Act: -0.1700
Data Index: 2599433 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.7982. Min Act: -0.1700
Data Index: 506318 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.7982. Min Act: -0.1700
Data Index: 905796 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.7670. Min Act: -0.1700
Data Index: 4488752 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3607. Min Range: -6.3607
Max Act: 5.7982. Min Act: -0.1700
Data Index: 3332335 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19