Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 252 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.6129. Min Act: -0.1700
Data Index: 1696899 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.4567. Min Act: -0.1700
Data Index: 5882819 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.3004. Min Act: -0.1700
Data Index: 6254877 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.2379. Min Act: -0.1700
Data Index: 4253624 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.2067. Min Act: -0.1700
Data Index: 7337121 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.2379. Min Act: -0.1700
Data Index: 1458206 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.2067. Min Act: -0.1700
Data Index: 8030760 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.1754. Min Act: -0.1700
Data Index: 6355892 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.1442. Min Act: -0.1700
Data Index: 1486227 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.1754. Min Act: -0.1700
Data Index: 2919237 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.1442. Min Act: -0.1700
Data Index: 4486936 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.1754. Min Act: -0.1700
Data Index: 8448468 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.1129. Min Act: -0.1700
Data Index: 328095 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.1129. Min Act: -0.1700
Data Index: 620828 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.1129. Min Act: -0.1700
Data Index: 7391338 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.1129. Min Act: -0.1700
Data Index: 3956015 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.0504. Min Act: -0.1700
Data Index: 3708242 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.1129. Min Act: -0.1700
Data Index: 5271795 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.0817. Min Act: -0.1700
Data Index: 614807 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6129. Min Range: -6.6129
Max Act: 6.1129. Min Act: -0.1700
Data Index: 6355890 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19