Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.7163. Min Act: -0.1700
Data Index: 8637915 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.7077. Min Act: -0.1700
Data Index: 6229251 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6990. Min Act: -0.1699
Data Index: 5394720 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6816. Min Act: -0.1700
Data Index: 7646479 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6642. Min Act: -0.1700
Data Index: 2632451 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6642. Min Act: -0.1697
Data Index: 6174069 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6556. Min Act: -0.1700
Data Index: 2487053 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6556. Min Act: -0.1700
Data Index: 4782985 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6556. Min Act: -0.1700
Data Index: 50712 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6556. Min Act: -0.1700
Data Index: 3327685 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6642. Min Act: -0.1699
Data Index: 687299 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6468. Min Act: -0.1700
Data Index: 8735272 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6468. Min Act: -0.1700
Data Index: 1973427 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6556. Min Act: -0.1700
Data Index: 7470183 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6381. Min Act: -0.1698
Data Index: 4632305 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6294. Min Act: -0.1700
Data Index: 7827888 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6294. Min Act: -0.1698
Data Index: 4620145 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6294. Min Act: -0.1698
Data Index: 509875 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6207. Min Act: -0.1700
Data Index: 698362 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7163. Min Range: -1.7163
Max Act: 1.6207. Min Act: -0.1601
Data Index: 5079700 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19