Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1601 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.6997. Min Act: -0.1700
Data Index: 1220470 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.6684. Min Act: -0.1699
Data Index: 3454808 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.6371. Min Act: -0.1700
Data Index: 6258888 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.6058. Min Act: -0.1700
Data Index: 4633672 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.6371. Min Act: -0.1700
Data Index: 3225576 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.6058. Min Act: -0.1700
Data Index: 5851013 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.6058. Min Act: -0.1700
Data Index: 363058 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.5745. Min Act: -0.1700
Data Index: 2113970 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.5745. Min Act: -0.1700
Data Index: 1907148 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.5432. Min Act: -0.1700
Data Index: 975742 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.6058. Min Act: -0.1700
Data Index: 3969202 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.5745. Min Act: -0.1700
Data Index: 5730500 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.5432. Min Act: -0.1700
Data Index: 6086464 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.5432. Min Act: -0.1700
Data Index: 6254537 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.5432. Min Act: -0.1700
Data Index: 1968345 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.5432. Min Act: -0.1699
Data Index: 8476814 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.5432. Min Act: -0.1700
Data Index: 3256606 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.5119. Min Act: -0.1700
Data Index: 5949469 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.5432. Min Act: -0.1700
Data Index: 2198899 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6997. Min Range: -3.6997
Max Act: 3.5119. Min Act: -0.1700
Data Index: 2696273 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19