Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.4788. Min Act: -0.1700
Data Index: 3119020 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.3538. Min Act: -0.1700
Data Index: 128529 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.2913. Min Act: -0.1700
Data Index: 5693703 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.2913. Min Act: -0.1700
Data Index: 8440698 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.2913. Min Act: -0.1700
Data Index: 7352058 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.2913. Min Act: -0.1700
Data Index: 7352057 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.2288. Min Act: -0.1700
Data Index: 8174566 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.1663. Min Act: -0.1700
Data Index: 8776816 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.1663. Min Act: -0.1700
Data Index: 5716674 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.1038. Min Act: -0.1700
Data Index: 1007140 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.1038. Min Act: -0.1700
Data Index: 8174567 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.1038. Min Act: -0.1700
Data Index: 3167353 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.1038. Min Act: -0.1700
Data Index: 2657194 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.1038. Min Act: -0.1700
Data Index: 7131724 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.1663. Min Act: -0.1700
Data Index: 6439701 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.1038. Min Act: -0.1700
Data Index: 5716678 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.0413. Min Act: -0.1700
Data Index: 5831590 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.0413. Min Act: -0.1700
Data Index: 3597829 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4788. Min Range: -8.4788
Max Act: 8.0413. Min Act: -0.1700
Data Index: 5831585 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4788. Min Range: -8.4788
Max Act: 7.9788. Min Act: -0.1700
Data Index: 4789211 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19