Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2743 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0306. Min Range: -4.0306
Max Act: 4.0306. Min Act: -0.1700
Data Index: 1423258 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0306. Min Range: -4.0306
Max Act: 4.0306. Min Act: -0.1700
Data Index: 280760 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0306. Min Range: -4.0306
Max Act: 4.0306. Min Act: -0.1700
Data Index: 5950010 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0306. Min Range: -4.0306
Max Act: 4.0306. Min Act: -0.1700
Data Index: 3150729 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0306. Min Range: -4.0306
Max Act: 4.0306. Min Act: -0.1700
Data Index: 8806726 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0306. Min Range: -4.0306
Max Act: 4.0306. Min Act: -0.1700
Data Index: 3552020 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0306. Min Range: -4.0306
Max Act: 4.0306. Min Act: -0.1700
Data Index: 1489143 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0306. Min Range: -4.0306
Max Act: 4.0306. Min Act: -0.1700
Data Index: 7791693 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0306. Min Range: -4.0306
Max Act: 4.0306. Min Act: -0.1700
Data Index: 7445475 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0306. Min Range: -4.0306
Max Act: 4.0306. Min Act: -0.1700
Data Index: 4157688 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0306. Min Range: -4.0306
Max Act: 3.9680. Min Act: -0.1700
Data Index: 5135878 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0306. Min Range: -4.0306
Max Act: 3.9368. Min Act: -0.1700
Data Index: 1861659 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0306. Min Range: -4.0306
Max Act: 3.8743. Min Act: -0.1700
Data Index: 4193700 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0306. Min Range: -4.0306
Max Act: 3.9055. Min Act: -0.1700
Data Index: 473139 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0306. Min Range: -4.0306
Max Act: 3.8743. Min Act: -0.1700
Data Index: 1984367 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0306. Min Range: -4.0306
Max Act: 3.8743. Min Act: -0.1700
Data Index: 7224945 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0306. Min Range: -4.0306
Max Act: 3.8430. Min Act: -0.1700
Data Index: 4401102 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0306. Min Range: -4.0306
Max Act: 3.8430. Min Act: -0.1700
Data Index: 7056828 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0306. Min Range: -4.0306
Max Act: 3.8430. Min Act: -0.1700
Data Index: 6460366 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0306. Min Range: -4.0306
Max Act: 3.8430. Min Act: -0.1700
Data Index: 2336403 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19