Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.7783. Min Act: -0.1700
Data Index: 8276941 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.8095. Min Act: -0.1700
Data Index: 6242089 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.5908. Min Act: -0.1700
Data Index: 8686659 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.5908. Min Act: -0.1700
Data Index: 5196761 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.5908. Min Act: -0.1700
Data Index: 6860981 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.5283. Min Act: -0.1700
Data Index: 6005129 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.4970. Min Act: -0.1700
Data Index: 6711487 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.5283. Min Act: -0.1700
Data Index: 3575362 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.4658. Min Act: -0.1700
Data Index: 3621711 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.4658. Min Act: -0.1700
Data Index: 4165902 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.5595. Min Act: -0.1700
Data Index: 1699287 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.4970. Min Act: -0.1700
Data Index: 8565424 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.4970. Min Act: -0.1700
Data Index: 8393965 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.4658. Min Act: -0.1700
Data Index: 7719682 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.4658. Min Act: -0.1700
Data Index: 1494348 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.4970. Min Act: -0.1700
Data Index: 2833451 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.4033. Min Act: -0.1700
Data Index: 1124964 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.4658. Min Act: -0.1700
Data Index: 8011240 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.4658. Min Act: -0.1700
Data Index: 49744 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8095. Min Range: -4.8095
Max Act: 4.4658. Min Act: -0.1700
Data Index: 8200311 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19