Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 812 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.9940. Min Act: -0.1700
Data Index: 6088606 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.9940. Min Act: -0.1700
Data Index: 2364736 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.9940. Min Act: -0.1700
Data Index: 7952428 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.9627. Min Act: -0.1700
Data Index: 891962 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.9002. Min Act: -0.1700
Data Index: 6915106 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.9002. Min Act: -0.1700
Data Index: 6409842 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.9002. Min Act: -0.1700
Data Index: 6496926 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.9002. Min Act: -0.1700
Data Index: 2047973 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8377. Min Act: -0.1700
Data Index: 3627746 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8690. Min Act: -0.1700
Data Index: 7173623 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8690. Min Act: -0.1700
Data Index: 797795 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8377. Min Act: -0.1700
Data Index: 854788 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8377. Min Act: -0.1700
Data Index: 93499 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8377. Min Act: -0.1700
Data Index: 116449 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8065. Min Act: -0.1700
Data Index: 4507536 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8377. Min Act: -0.1700
Data Index: 3589043 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8065. Min Act: -0.1700
Data Index: 6908254 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.7752. Min Act: -0.1700
Data Index: 4287137 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8377. Min Act: -0.1700
Data Index: 3428353 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.7752. Min Act: -0.1700
Data Index: 2274120 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19