Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5838 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8874. Min Range: -10.8874
Max Act: 10.8874. Min Act: -0.1700
Data Index: 3329709 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8874. Min Range: -10.8874
Max Act: 10.6999. Min Act: -0.1700
Data Index: 3371752 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8874. Min Range: -10.8874
Max Act: 10.2624. Min Act: -0.1700
Data Index: 2585529 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8874. Min Range: -10.8874
Max Act: 10.3249. Min Act: -0.1700
Data Index: 5366608 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8874. Min Range: -10.8874
Max Act: 10.1999. Min Act: -0.1700
Data Index: 8225247 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8874. Min Range: -10.8874
Max Act: 10.1999. Min Act: -0.1700
Data Index: 3852914 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8874. Min Range: -10.8874
Max Act: 10.1374. Min Act: -0.1700
Data Index: 1530411 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8874. Min Range: -10.8874
Max Act: 10.1999. Min Act: -0.1700
Data Index: 8275951 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8874. Min Range: -10.8874
Max Act: 10.1374. Min Act: -0.1700
Data Index: 6850333 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8874. Min Range: -10.8874
Max Act: 10.0124. Min Act: -0.1700
Data Index: 7054694 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8874. Min Range: -10.8874
Max Act: 10.0124. Min Act: -0.1700
Data Index: 5029285 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8874. Min Range: -10.8874
Max Act: 9.9499. Min Act: -0.1699
Data Index: 2238185 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8874. Min Range: -10.8874
Max Act: 9.9499. Min Act: -0.1700
Data Index: 8632580 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8874. Min Range: -10.8874
Max Act: 9.9499. Min Act: -0.1700
Data Index: 5734520 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8874. Min Range: -10.8874
Max Act: 9.9499. Min Act: -0.1700
Data Index: 4949102 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8874. Min Range: -10.8874
Max Act: 9.8874. Min Act: -0.1700
Data Index: 3794395 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8874. Min Range: -10.8874
Max Act: 9.8874. Min Act: -0.1700
Data Index: 1372311 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8874. Min Range: -10.8874
Max Act: 9.8874. Min Act: -0.1700
Data Index: 5996905 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8874. Min Range: -10.8874
Max Act: 9.8249. Min Act: -0.1700
Data Index: 5946920 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8874. Min Range: -10.8874
Max Act: 9.8249. Min Act: -0.1698
Data Index: 3852400 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19