Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3918 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.4113. Min Act: -0.1700
Data Index: 2330921 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.3488. Min Act: -0.1700
Data Index: 7314010 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.3488. Min Act: -0.1699
Data Index: 7469909 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.3176. Min Act: -0.1700
Data Index: 169898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2863. Min Act: -0.1698
Data Index: 5619400 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2863. Min Act: -0.1700
Data Index: 25341 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2863. Min Act: -0.1700
Data Index: 820345 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2551. Min Act: -0.1700
Data Index: 4832143 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2551. Min Act: -0.1696
Data Index: 1199331 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2551. Min Act: -0.1700
Data Index: 3491548 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2551. Min Act: -0.1700
Data Index: 3994773 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2551. Min Act: -0.1700
Data Index: 5678797 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2238. Min Act: -0.1700
Data Index: 355710 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2238. Min Act: -0.1687
Data Index: 2024410 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2551. Min Act: -0.1700
Data Index: 180126 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2238. Min Act: -0.1640
Data Index: 1481506 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.1926. Min Act: -0.1700
Data Index: 1698418 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.1926. Min Act: -0.1700
Data Index: 481429 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.1926. Min Act: -0.1700
Data Index: 1079709 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4113. Min Range: -5.4113
Max Act: 5.2238. Min Act: -0.1671
Data Index: 1165629 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19