Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2624 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.1240. Min Act: -0.1700
Data Index: 6298088 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.1240. Min Act: -0.1700
Data Index: 6660688 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.1240. Min Act: -0.1700
Data Index: 4155498 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0928. Min Act: -0.1700
Data Index: 1501944 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0928. Min Act: -0.1700
Data Index: 7730801 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0303. Min Act: -0.1700
Data Index: 8407719 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0615. Min Act: -0.1700
Data Index: 1966320 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0615. Min Act: -0.1700
Data Index: 5498060 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0615. Min Act: -0.1700
Data Index: 4636879 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0303. Min Act: -0.1700
Data Index: 1011904 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0303. Min Act: -0.1700
Data Index: 1719992 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0615. Min Act: -0.1700
Data Index: 4197958 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0928. Min Act: -0.1700
Data Index: 6288497 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0303. Min Act: -0.1700
Data Index: 4151127 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0303. Min Act: -0.1700
Data Index: 3507457 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0303. Min Act: -0.1700
Data Index: 1471682 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0303. Min Act: -0.1700
Data Index: 6929084 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1240. Min Range: -5.1240
Max Act: 4.9990. Min Act: -0.1700
Data Index: 4822478 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0303. Min Act: -0.1700
Data Index: 1831477 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1240. Min Range: -5.1240
Max Act: 5.0615. Min Act: -0.1700
Data Index: 1226808 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19