Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4909. Min Range: -7.4909
Max Act: 7.4909. Min Act: -0.1700
Data Index: 2796085 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4909. Min Range: -7.4909
Max Act: 7.4284. Min Act: -0.1700
Data Index: 3561244 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4909. Min Range: -7.4909
Max Act: 7.2097. Min Act: -0.1700
Data Index: 1523903 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4909. Min Range: -7.4909
Max Act: 7.1784. Min Act: -0.1700
Data Index: 4411569 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4909. Min Range: -7.4909
Max Act: 7.0847. Min Act: -0.1700
Data Index: 561050 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4909. Min Range: -7.4909
Max Act: 7.0847. Min Act: -0.1700
Data Index: 347771 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4909. Min Range: -7.4909
Max Act: 7.0534. Min Act: -0.1700
Data Index: 262522 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4909. Min Range: -7.4909
Max Act: 7.0534. Min Act: -0.1700
Data Index: 3221234 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4909. Min Range: -7.4909
Max Act: 7.0222. Min Act: -0.1700
Data Index: 6699651 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4909. Min Range: -7.4909
Max Act: 6.9909. Min Act: -0.1700
Data Index: 5630026 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4909. Min Range: -7.4909
Max Act: 6.9597. Min Act: -0.1700
Data Index: 4594071 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4909. Min Range: -7.4909
Max Act: 6.9909. Min Act: -0.1700
Data Index: 4493704 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4909. Min Range: -7.4909
Max Act: 6.9284. Min Act: -0.1700
Data Index: 5103403 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4909. Min Range: -7.4909
Max Act: 6.9284. Min Act: -0.1700
Data Index: 4601541 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4909. Min Range: -7.4909
Max Act: 6.9284. Min Act: -0.1700
Data Index: 7531839 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4909. Min Range: -7.4909
Max Act: 6.9284. Min Act: -0.1700
Data Index: 6711823 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4909. Min Range: -7.4909
Max Act: 6.9284. Min Act: -0.1700
Data Index: 34156 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4909. Min Range: -7.4909
Max Act: 6.9284. Min Act: -0.1700
Data Index: 1603087 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4909. Min Range: -7.4909
Max Act: 6.8659. Min Act: -0.1700
Data Index: 2251279 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4909. Min Range: -7.4909
Max Act: 6.8972. Min Act: -0.1700
Data Index: 4625960 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19