Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1042. Min Range: -6.1042
Max Act: 6.1042. Min Act: -0.1700
Data Index: 1441962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1042. Min Range: -6.1042
Max Act: 6.0105. Min Act: -0.1700
Data Index: 8796523 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.9167. Min Act: -0.1700
Data Index: 2424837 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.9167. Min Act: -0.1700
Data Index: 6949279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.9167. Min Act: -0.1700
Data Index: 4422159 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.9167. Min Act: -0.1700
Data Index: 3402453 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.9167. Min Act: -0.1700
Data Index: 586600 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.8855. Min Act: -0.1700
Data Index: 2773712 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.9167. Min Act: -0.1685
Data Index: 5449503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.8855. Min Act: -0.1700
Data Index: 2486473 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.8855. Min Act: -0.1700
Data Index: 7071046 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.8855. Min Act: -0.1700
Data Index: 901865 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.8542. Min Act: -0.1700
Data Index: 2260510 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.8855. Min Act: -0.1700
Data Index: 3142128 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.8542. Min Act: -0.1700
Data Index: 1999799 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.8542. Min Act: -0.1698
Data Index: 3321647 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.8542. Min Act: -0.1700
Data Index: 378288 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.8542. Min Act: -0.1700
Data Index: 3382754 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.8542. Min Act: -0.1700
Data Index: 1071129 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1042. Min Range: -6.1042
Max Act: 5.8542. Min Act: -0.1700
Data Index: 489787 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19