Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4037 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0849. Min Range: -9.0849
Max Act: 9.0849. Min Act: -0.1700
Data Index: 7828997 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.5224. Min Act: -0.1700
Data Index: 3691979 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.5224. Min Act: -0.1700
Data Index: 4410792 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.4599. Min Act: -0.1700
Data Index: 6965765 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.3974. Min Act: -0.1700
Data Index: 2482707 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.3974. Min Act: -0.1700
Data Index: 8801297 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.3974. Min Act: -0.1700
Data Index: 4614473 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.3974. Min Act: -0.1700
Data Index: 7485762 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.3349. Min Act: -0.1700
Data Index: 2754985 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.3349. Min Act: -0.1700
Data Index: 5797425 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.2724. Min Act: -0.1700
Data Index: 578602 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.2099. Min Act: -0.1700
Data Index: 6631030 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.2099. Min Act: -0.1700
Data Index: 2866076 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.1787. Min Act: -0.1700
Data Index: 4279437 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.1162. Min Act: -0.1700
Data Index: 1053823 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.1474. Min Act: -0.1700
Data Index: 4193639 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.1162. Min Act: -0.1700
Data Index: 2794729 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.1474. Min Act: -0.1700
Data Index: 8790067 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.0537. Min Act: -0.1700
Data Index: 1446857 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.1162. Min Act: -0.1700
Data Index: 1056300 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19