Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4683 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1144. Min Range: -5.1144
Max Act: 5.1144. Min Act: -0.1700
Data Index: 6133135 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.9894. Min Act: -0.1700
Data Index: 8788040 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.8644. Min Act: -0.1700
Data Index: 6203832 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.6456. Min Act: -0.1700
Data Index: 2439847 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.6456. Min Act: -0.1700
Data Index: 6879006 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.6456. Min Act: -0.1700
Data Index: 3815684 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.6144. Min Act: -0.1700
Data Index: 6112158 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.6144. Min Act: -0.1700
Data Index: 2925295 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.6144. Min Act: -0.1700
Data Index: 6920841 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.5519. Min Act: -0.1700
Data Index: 6306418 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.5519. Min Act: -0.1700
Data Index: 634506 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.5831. Min Act: -0.1700
Data Index: 7773021 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.5519. Min Act: -0.1700
Data Index: 705812 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.5831. Min Act: -0.1700
Data Index: 3344039 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.5831. Min Act: -0.1700
Data Index: 576088 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.5206. Min Act: -0.1700
Data Index: 7151580 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.5519. Min Act: -0.1700
Data Index: 8620016 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.5519. Min Act: -0.1700
Data Index: 6686387 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.5206. Min Act: -0.1700
Data Index: 8287043 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.5519. Min Act: -0.1700
Data Index: 2398257 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19