Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.7741. Min Act: -0.1700
Data Index: 947031 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.7429. Min Act: -0.1700
Data Index: 5882250 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.7116. Min Act: -0.1700
Data Index: 4125552 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.6804. Min Act: -0.1700
Data Index: 8324320 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.6804. Min Act: -0.1700
Data Index: 8703487 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.6491. Min Act: -0.1700
Data Index: 4328869 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.6491. Min Act: -0.1700
Data Index: 4705474 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.6491. Min Act: -0.1700
Data Index: 2559146 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.6491. Min Act: -0.1700
Data Index: 2816893 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.6491. Min Act: -0.1700
Data Index: 8361014 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.6179. Min Act: -0.1700
Data Index: 1367194 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.6491. Min Act: -0.1700
Data Index: 5103378 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.6179. Min Act: -0.1700
Data Index: 4280465 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.6179. Min Act: -0.1700
Data Index: 7408496 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.5866. Min Act: -0.1700
Data Index: 4452122 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.5866. Min Act: -0.1700
Data Index: 947035 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.5866. Min Act: -0.1700
Data Index: 7260814 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.6179. Min Act: -0.1700
Data Index: 1665835 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.5554. Min Act: -0.1700
Data Index: 2631594 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7741. Min Range: -4.7741
Max Act: 4.5866. Min Act: -0.1700
Data Index: 1240945 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19