Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4863 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0642. Min Range: -6.0642
Max Act: 6.0642. Min Act: -0.1700
Data Index: 6995363 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.7830. Min Act: -0.1700
Data Index: 6374635 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.7517. Min Act: -0.1700
Data Index: 6669819 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.7830. Min Act: -0.1700
Data Index: 8696095 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.7830. Min Act: -0.1700
Data Index: 8641188 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.7205. Min Act: -0.1700
Data Index: 5032299 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.6892. Min Act: -0.1700
Data Index: 4828376 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.6580. Min Act: -0.1700
Data Index: 6496334 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.6580. Min Act: -0.1700
Data Index: 676594 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.6267. Min Act: -0.1700
Data Index: 1006745 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.6580. Min Act: -0.1700
Data Index: 1440369 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.6580. Min Act: -0.1700
Data Index: 3400376 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.6892. Min Act: -0.1700
Data Index: 5007875 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.5955. Min Act: -0.1700
Data Index: 7910211 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.5955. Min Act: -0.1700
Data Index: 6654608 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.6267. Min Act: -0.1700
Data Index: 7332911 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.6267. Min Act: -0.1700
Data Index: 3157808 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.5955. Min Act: -0.1700
Data Index: 5194377 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.5955. Min Act: -0.1700
Data Index: 5660905 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0642. Min Range: -6.0642
Max Act: 5.5955. Min Act: -0.1700
Data Index: 5783060 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19