Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2214 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.4604. Min Act: -0.1700
Data Index: 7219906 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.3979. Min Act: -0.1700
Data Index: 7300477 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.2729. Min Act: -0.1700
Data Index: 4579435 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.2417. Min Act: -0.1700
Data Index: 6595308 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.1479. Min Act: -0.1700
Data Index: 3217399 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.1479. Min Act: -0.1700
Data Index: 2877077 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.1167. Min Act: -0.1700
Data Index: 2877089 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.1167. Min Act: -0.1700
Data Index: 2232086 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.0542. Min Act: -0.1700
Data Index: 806230 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4604. Min Range: -6.4604
Max Act: 6.0542. Min Act: -0.1700
Data Index: 5266292 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.9604. Min Act: -0.1700
Data Index: 6122355 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.8979. Min Act: -0.1700
Data Index: 6565624 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.9292. Min Act: -0.1700
Data Index: 5627098 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.9292. Min Act: -0.1700
Data Index: 4433797 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.9292. Min Act: -0.1700
Data Index: 8436702 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.8979. Min Act: -0.1700
Data Index: 386294 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.8979. Min Act: -0.1700
Data Index: 2238750 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.8979. Min Act: -0.1700
Data Index: 1679251 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.8979. Min Act: -0.1700
Data Index: 7219907 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4604. Min Range: -6.4604
Max Act: 5.8667. Min Act: -0.1700
Data Index: 6565634 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19