Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 900 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.8713. Min Act: -0.1700
Data Index: 4749461 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.8400. Min Act: -0.1700
Data Index: 1436141 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.8400. Min Act: -0.1700
Data Index: 4994215 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7775. Min Act: -0.1700
Data Index: 7732671 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.8400. Min Act: -0.1700
Data Index: 5094329 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.8088. Min Act: -0.1700
Data Index: 4111018 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7775. Min Act: -0.1700
Data Index: 6016344 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.8088. Min Act: -0.1700
Data Index: 6051479 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7775. Min Act: -0.1700
Data Index: 4190628 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7775. Min Act: -0.1700
Data Index: 5092669 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7775. Min Act: -0.1700
Data Index: 5813213 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7775. Min Act: -0.1700
Data Index: 968921 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7775. Min Act: -0.1700
Data Index: 1451804 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7463. Min Act: -0.1700
Data Index: 290732 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7463. Min Act: -0.1700
Data Index: 1150640 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7463. Min Act: -0.1700
Data Index: 5266872 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7463. Min Act: -0.1700
Data Index: 5698099 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7463. Min Act: -0.1700
Data Index: 283192 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7463. Min Act: -0.1700
Data Index: 7712279 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8713. Min Range: -4.8713
Max Act: 4.7463. Min Act: -0.1700
Data Index: 3721015 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19