Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.8129. Min Act: -0.1700
Data Index: 2635609 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.7504. Min Act: -0.1700
Data Index: 7659800 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.7504. Min Act: -0.1700
Data Index: 2041144 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.7191. Min Act: -0.1700
Data Index: 7297012 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.7191. Min Act: -0.1700
Data Index: 8464909 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.7191. Min Act: -0.1700
Data Index: 7347049 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6879. Min Act: -0.1700
Data Index: 5226783 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6566. Min Act: -0.1700
Data Index: 7892009 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6879. Min Act: -0.1700
Data Index: 1730590 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6566. Min Act: -0.1700
Data Index: 6782298 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6254. Min Act: -0.1700
Data Index: 4997046 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6566. Min Act: -0.1700
Data Index: 518358 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6254. Min Act: -0.1700
Data Index: 2746791 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6254. Min Act: -0.1700
Data Index: 7195050 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6254. Min Act: -0.1700
Data Index: 337386 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6254. Min Act: -0.1700
Data Index: 802443 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6254. Min Act: -0.1700
Data Index: 2318692 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6254. Min Act: -0.1700
Data Index: 8019946 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6254. Min Act: -0.1700
Data Index: 1008563 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8129. Min Range: -5.8129
Max Act: 5.6254. Min Act: -0.1700
Data Index: 1037641 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19