Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 328 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.6052. Min Act: -0.1700
Data Index: 6474051 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.6052. Min Act: -0.1700
Data Index: 7053365 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.5269. Min Act: -0.1700
Data Index: 1048770 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.4330. Min Act: -0.1700
Data Index: 6534771 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.4330. Min Act: -0.1700
Data Index: 2095813 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.4173. Min Act: -0.1700
Data Index: 3724135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.4173. Min Act: -0.1700
Data Index: 2448542 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.3859. Min Act: -0.1700
Data Index: 2796013 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.4016. Min Act: -0.1700
Data Index: 94022 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.4016. Min Act: -0.1700
Data Index: 5854175 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.3859. Min Act: -0.1700
Data Index: 1625806 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.3859. Min Act: -0.1700
Data Index: 5795526 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.3702. Min Act: -0.1700
Data Index: 3137165 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.3702. Min Act: -0.1700
Data Index: 8108204 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.3702. Min Act: -0.1700
Data Index: 6361885 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.3546. Min Act: -0.1700
Data Index: 4875554 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.2918. Min Act: -0.1700
Data Index: 1815197 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.3389. Min Act: -0.1700
Data Index: 94021 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.3389. Min Act: -0.1700
Data Index: 6899842 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6052. Min Range: -3.6052
Max Act: 3.3546. Min Act: -0.1700
Data Index: 3075422 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19