Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5949. Min Range: -6.5949
Max Act: 6.5949. Min Act: -0.1700
Data Index: 5811399 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5949. Min Range: -6.5949
Max Act: 6.3762. Min Act: -0.1700
Data Index: 1682884 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5949. Min Range: -6.5949
Max Act: 6.2824. Min Act: -0.1700
Data Index: 8637385 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5949. Min Range: -6.5949
Max Act: 6.1887. Min Act: -0.1700
Data Index: 2041745 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5949. Min Range: -6.5949
Max Act: 6.1574. Min Act: -0.1700
Data Index: 7472004 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5949. Min Range: -6.5949
Max Act: 6.0637. Min Act: -0.1700
Data Index: 2367446 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5949. Min Range: -6.5949
Max Act: 6.0012. Min Act: -0.1700
Data Index: 8521308 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5949. Min Range: -6.5949
Max Act: 6.0012. Min Act: -0.1700
Data Index: 49569 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5949. Min Range: -6.5949
Max Act: 5.9699. Min Act: -0.1700
Data Index: 4898530 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5949. Min Range: -6.5949
Max Act: 5.9699. Min Act: -0.1700
Data Index: 2574867 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5949. Min Range: -6.5949
Max Act: 5.9387. Min Act: -0.1700
Data Index: 1280028 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5949. Min Range: -6.5949
Max Act: 5.9387. Min Act: -0.1700
Data Index: 368244 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5949. Min Range: -6.5949
Max Act: 5.9387. Min Act: -0.1700
Data Index: 2167588 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5949. Min Range: -6.5949
Max Act: 5.9387. Min Act: -0.1700
Data Index: 444383 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5949. Min Range: -6.5949
Max Act: 5.9074. Min Act: -0.1700
Data Index: 3804628 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5949. Min Range: -6.5949
Max Act: 5.8762. Min Act: -0.1700
Data Index: 7890664 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5949. Min Range: -6.5949
Max Act: 5.8762. Min Act: -0.1700
Data Index: 3341283 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5949. Min Range: -6.5949
Max Act: 5.9074. Min Act: -0.1700
Data Index: 952990 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5949. Min Range: -6.5949
Max Act: 5.9074. Min Act: -0.1700
Data Index: 6791297 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5949. Min Range: -6.5949
Max Act: 5.8762. Min Act: -0.1700
Data Index: 2553699 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19