Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4731 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.2741. Min Act: -0.1700
Data Index: 7035825 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.2741. Min Act: -0.1700
Data Index: 867854 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.2427. Min Act: -0.1700
Data Index: 6798168 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.2584. Min Act: -0.1700
Data Index: 2186813 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.2427. Min Act: -0.1700
Data Index: 867852 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.2584. Min Act: -0.1700
Data Index: 221126 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.2269. Min Act: -0.1700
Data Index: 8265854 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.2112. Min Act: -0.1700
Data Index: 3415714 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.2269. Min Act: -0.1700
Data Index: 3548457 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.1798. Min Act: -0.1700
Data Index: 5731116 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.1798. Min Act: -0.1700
Data Index: 928627 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.1798. Min Act: -0.1700
Data Index: 4255732 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.1640. Min Act: -0.1700
Data Index: 2986110 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.1640. Min Act: -0.1700
Data Index: 1727429 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.1798. Min Act: -0.1700
Data Index: 4835318 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.1640. Min Act: -0.1700
Data Index: 6512884 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.1640. Min Act: -0.1700
Data Index: 1131029 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.1483. Min Act: -0.1700
Data Index: 4714663 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.1325. Min Act: -0.1700
Data Index: 7250113 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2741. Min Range: -3.2741
Max Act: 3.1325. Min Act: -0.1700
Data Index: 6052754 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19