Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 447 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.9801. Min Act: -0.1700
Data Index: 2183426 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.7301. Min Act: -0.1700
Data Index: 6490879 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.6676. Min Act: -0.1700
Data Index: 8583376 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.5739. Min Act: -0.1700
Data Index: 2750542 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.5426. Min Act: -0.1700
Data Index: 8496249 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.4489. Min Act: -0.1700
Data Index: 4899576 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.4489. Min Act: -0.1700
Data Index: 4238816 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.4176. Min Act: -0.1700
Data Index: 6022570 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.3864. Min Act: -0.1700
Data Index: 6687081 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.3551. Min Act: -0.1700
Data Index: 2994614 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.3551. Min Act: -0.1700
Data Index: 5454157 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.3551. Min Act: -0.1700
Data Index: 5779672 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.3239. Min Act: -0.1700
Data Index: 5659207 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.3239. Min Act: -0.1700
Data Index: 8446425 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.2926. Min Act: -0.1700
Data Index: 5655016 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.2926. Min Act: -0.1700
Data Index: 5086153 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.2301. Min Act: -0.1700
Data Index: 1549823 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.2614. Min Act: -0.1700
Data Index: 3049385 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.2301. Min Act: -0.1700
Data Index: 7417466 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9801. Min Range: -6.9801
Max Act: 6.2301. Min Act: -0.1700
Data Index: 7376699 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19