Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 384 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.6389. Min Act: -0.1696
Data Index: 8103991 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.6215. Min Act: -0.1700
Data Index: 2302456 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5953. Min Act: -0.1697
Data Index: 5386368 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.6040. Min Act: -0.1700
Data Index: 2550857 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5866. Min Act: -0.1700
Data Index: 1329612 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5866. Min Act: -0.1700
Data Index: 130149 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1682
Data Index: 4837757 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1700
Data Index: 4789076 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1697
Data Index: 4641322 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1699
Data Index: 1412487 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1700
Data Index: 2493611 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1700
Data Index: 2664662 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1699
Data Index: 2556328 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1700
Data Index: 954284 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1685
Data Index: 3988961 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1700
Data Index: 1390328 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1688
Data Index: 2177880 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1700
Data Index: 564689 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1700
Data Index: 2243932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6389. Min Range: -1.6389
Max Act: 1.5691. Min Act: -0.1694
Data Index: 3988512 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19