Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5339 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.9892. Min Act: -0.1681
Data Index: 2289535 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.8329. Min Act: -0.1674
Data Index: 5178561 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.7704. Min Act: -0.1669
Data Index: 5607626 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.7391. Min Act: -0.1700
Data Index: 4628559 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.7391. Min Act: -0.1693
Data Index: 7844498 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.7078. Min Act: -0.1695
Data Index: 8310806 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.7078. Min Act: -0.1700
Data Index: 4583774 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6765. Min Act: -0.1692
Data Index: 5097097 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6452. Min Act: -0.1679
Data Index: 7229291 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6452. Min Act: -0.1700
Data Index: 3887828 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6139. Min Act: -0.1700
Data Index: 7520900 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6139. Min Act: -0.1699
Data Index: 5122647 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6139. Min Act: -0.1687
Data Index: 7758087 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6139. Min Act: -0.1694
Data Index: 3712980 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6139. Min Act: -0.1699
Data Index: 969049 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6139. Min Act: -0.1655
Data Index: 7047364 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6139. Min Act: -0.1677
Data Index: 6772488 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6452. Min Act: -0.1693
Data Index: 2289046 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6452. Min Act: -0.1697
Data Index: 6009993 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9892. Min Range: -3.9892
Max Act: 3.6139. Min Act: -0.1698
Data Index: 5695361 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19