Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2578. Min Range: -5.2578
Max Act: 5.2578. Min Act: -0.1700
Data Index: 3563138 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2578. Min Range: -5.2578
Max Act: 5.1328. Min Act: -0.1700
Data Index: 2968161 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2578. Min Range: -5.2578
Max Act: 5.0703. Min Act: -0.1700
Data Index: 69394 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2578. Min Range: -5.2578
Max Act: 5.1016. Min Act: -0.1700
Data Index: 3208321 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2578. Min Range: -5.2578
Max Act: 5.0391. Min Act: -0.1700
Data Index: 7332483 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2578. Min Range: -5.2578
Max Act: 5.0703. Min Act: -0.1700
Data Index: 4683505 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2578. Min Range: -5.2578
Max Act: 5.0391. Min Act: -0.1700
Data Index: 5239016 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2578. Min Range: -5.2578
Max Act: 5.0391. Min Act: -0.1700
Data Index: 2728965 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2578. Min Range: -5.2578
Max Act: 5.0078. Min Act: -0.1700
Data Index: 2548767 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2578. Min Range: -5.2578
Max Act: 5.0078. Min Act: -0.1700
Data Index: 1542307 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2578. Min Range: -5.2578
Max Act: 5.0078. Min Act: -0.1700
Data Index: 3799234 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2578. Min Range: -5.2578
Max Act: 4.9766. Min Act: -0.1700
Data Index: 5967605 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2578. Min Range: -5.2578
Max Act: 4.9453. Min Act: -0.1700
Data Index: 5763016 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2578. Min Range: -5.2578
Max Act: 4.9766. Min Act: -0.1700
Data Index: 3883258 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2578. Min Range: -5.2578
Max Act: 4.9453. Min Act: -0.1700
Data Index: 3392886 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2578. Min Range: -5.2578
Max Act: 4.9453. Min Act: -0.1700
Data Index: 3653917 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2578. Min Range: -5.2578
Max Act: 4.9141. Min Act: -0.1700
Data Index: 149003 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2578. Min Range: -5.2578
Max Act: 4.9453. Min Act: -0.1700
Data Index: 2881724 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2578. Min Range: -5.2578
Max Act: 4.9453. Min Act: -0.1700
Data Index: 3509808 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2578. Min Range: -5.2578
Max Act: 4.9766. Min Act: -0.1700
Data Index: 7075205 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19