Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.5180. Min Act: -0.1700
Data Index: 1432747 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.2680. Min Act: -0.1700
Data Index: 927267 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.2367. Min Act: -0.1700
Data Index: 1166646 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.2367. Min Act: -0.1700
Data Index: 4499488 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.2367. Min Act: -0.1700
Data Index: 7001746 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.2055. Min Act: -0.1700
Data Index: 411090 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.1742. Min Act: -0.1700
Data Index: 1765464 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.1742. Min Act: -0.1700
Data Index: 3005287 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.0805. Min Act: -0.1700
Data Index: 3843271 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.0492. Min Act: -0.1700
Data Index: 518442 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.0492. Min Act: -0.1700
Data Index: 2290539 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.0180. Min Act: -0.1700
Data Index: 4793119 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5180. Min Range: -5.5180
Max Act: 4.9867. Min Act: -0.1700
Data Index: 8264922 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.0180. Min Act: -0.1700
Data Index: 5634017 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.0180. Min Act: -0.1700
Data Index: 6138190 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.0180. Min Act: -0.1700
Data Index: 1850159 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.0180. Min Act: -0.1700
Data Index: 3659726 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5180. Min Range: -5.5180
Max Act: 5.0180. Min Act: -0.1700
Data Index: 3876811 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5180. Min Range: -5.5180
Max Act: 4.9867. Min Act: -0.1700
Data Index: 5985877 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5180. Min Range: -5.5180
Max Act: 4.9867. Min Act: -0.1700
Data Index: 3750237 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19