Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1640 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.9389. Min Act: -0.1700
Data Index: 7486031 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.9077. Min Act: -0.1700
Data Index: 1053629 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.7514. Min Act: -0.1700
Data Index: 3661704 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.6889. Min Act: -0.1700
Data Index: 4805774 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.6577. Min Act: -0.1700
Data Index: 6773168 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.6577. Min Act: -0.1700
Data Index: 818627 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.6577. Min Act: -0.1700
Data Index: 5516341 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.6264. Min Act: -0.1700
Data Index: 4414049 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.6264. Min Act: -0.1700
Data Index: 1130405 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.5639. Min Act: -0.1700
Data Index: 4608448 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.5952. Min Act: -0.1700
Data Index: 8239676 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.6264. Min Act: -0.1700
Data Index: 5836196 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.5639. Min Act: -0.1700
Data Index: 8723606 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.5639. Min Act: -0.1700
Data Index: 2389440 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.5639. Min Act: -0.1700
Data Index: 7485176 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.5639. Min Act: -0.1700
Data Index: 6426620 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.5327. Min Act: -0.1700
Data Index: 1045474 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.5327. Min Act: -0.1700
Data Index: 3396060 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.5639. Min Act: -0.1700
Data Index: 801126 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9389. Min Range: -5.9389
Max Act: 5.5014. Min Act: -0.1700
Data Index: 4962884 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19