Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 306 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0767. Min Range: -10.0767
Max Act: 10.0767. Min Act: -0.1699
Data Index: 1312121 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0767. Min Range: -10.0767
Max Act: 10.0767. Min Act: -0.1700
Data Index: 5514212 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.9517. Min Act: -0.1700
Data Index: 8470063 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0767. Min Range: -10.0767
Max Act: 10.0767. Min Act: -0.1700
Data Index: 3574510 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.8892. Min Act: -0.1700
Data Index: 4802251 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.8892. Min Act: -0.1700
Data Index: 7671194 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.8267. Min Act: -0.1700
Data Index: 3847638 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.8892. Min Act: -0.1700
Data Index: 2965719 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.8267. Min Act: -0.1682
Data Index: 2609541 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.8267. Min Act: -0.1700
Data Index: 1071314 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.7642. Min Act: -0.1700
Data Index: 8426013 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.7642. Min Act: -0.1700
Data Index: 2668220 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.7642. Min Act: -0.1700
Data Index: 4512568 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.8267. Min Act: -0.1700
Data Index: 8684623 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.7017. Min Act: -0.1700
Data Index: 5760044 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.6392. Min Act: -0.1700
Data Index: 777773 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.6392. Min Act: -0.1700
Data Index: 3508888 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.6392. Min Act: -0.1700
Data Index: 4672539 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.5767. Min Act: -0.1699
Data Index: 7850855 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0767. Min Range: -10.0767
Max Act: 9.6392. Min Act: -0.1700
Data Index: 8241082 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19