Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1591 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0615. Min Range: -1.0615
Max Act: 1.0615. Min Act: -0.1700
Data Index: 4859303 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0615. Min Range: -1.0615
Max Act: 1.0006. Min Act: -0.1691
Data Index: 3466407 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.9746. Min Act: -0.1682
Data Index: 1267280 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.9315. Min Act: -0.1685
Data Index: 3122291 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.9315. Min Act: -0.1700
Data Index: 1399063 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.9057. Min Act: -0.1693
Data Index: 7448067 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8972. Min Act: -0.1633
Data Index: 5435734 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8972. Min Act: -0.1699
Data Index: 7557607 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8972. Min Act: -0.1700
Data Index: 4558237 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8972. Min Act: -0.1700
Data Index: 6030639 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8801. Min Act: -0.1700
Data Index: 4943150 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8716. Min Act: -0.1700
Data Index: 5249245 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8716. Min Act: -0.1683
Data Index: 7491058 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8801. Min Act: -0.1684
Data Index: 5575660 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8546. Min Act: -0.1697
Data Index: 3771736 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8546. Min Act: -0.1675
Data Index: 5508343 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8631. Min Act: -0.1700
Data Index: 1616242 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8546. Min Act: -0.1700
Data Index: 111786 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8546. Min Act: -0.1700
Data Index: 4604391 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0615. Min Range: -1.0615
Max Act: 0.8546. Min Act: -0.1656
Data Index: 6485414 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19