Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2039 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.9729. Min Act: -0.1700
Data Index: 1199978 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.9559. Min Act: -0.1700
Data Index: 3569753 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.9389. Min Act: -0.1700
Data Index: 4794466 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8707. Min Act: -0.1700
Data Index: 5614498 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8536. Min Act: -0.1700
Data Index: 6429887 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8365. Min Act: -0.1700
Data Index: 4071907 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8193. Min Act: -0.1700
Data Index: 8219817 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8021. Min Act: -0.1700
Data Index: 8776409 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8193. Min Act: -0.1700
Data Index: 108542 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8193. Min Act: -0.1700
Data Index: 6461218 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8193. Min Act: -0.1700
Data Index: 80699 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8365. Min Act: -0.1700
Data Index: 7934594 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8021. Min Act: -0.1700
Data Index: 815660 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8193. Min Act: -0.1700
Data Index: 8208467 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8193. Min Act: -0.1700
Data Index: 1353187 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8021. Min Act: -0.1700
Data Index: 1903735 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8021. Min Act: -0.1700
Data Index: 4258525 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.7849. Min Act: -0.1700
Data Index: 6969574 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8193. Min Act: -0.1700
Data Index: 5227801 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9729. Min Range: -1.9729
Max Act: 1.8021. Min Act: -0.1700
Data Index: 5361069 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19