Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2391 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6602. Min Range: -12.6602
Max Act: 12.6602. Min Act: -0.1700
Data Index: 2937500 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6602. Min Range: -12.6602
Max Act: 12.4102. Min Act: -0.1700
Data Index: 822080 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6602. Min Range: -12.6602
Max Act: 12.1602. Min Act: -0.1700
Data Index: 269105 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6602. Min Range: -12.6602
Max Act: 12.0977. Min Act: -0.1700
Data Index: 4052146 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6602. Min Range: -12.6602
Max Act: 12.0977. Min Act: -0.1700
Data Index: 1517941 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6602. Min Range: -12.6602
Max Act: 12.0977. Min Act: -0.1700
Data Index: 1576204 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.9727. Min Act: -0.1700
Data Index: 3592060 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.9102. Min Act: -0.1700
Data Index: 4223198 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.8477. Min Act: -0.1700
Data Index: 8715157 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.7852. Min Act: -0.1700
Data Index: 558051 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.6602. Min Act: -0.1700
Data Index: 6382522 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.6602. Min Act: -0.1700
Data Index: 2540984 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.6602. Min Act: -0.1700
Data Index: 5865927 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.6602. Min Act: -0.1700
Data Index: 889580 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.5977. Min Act: -0.1700
Data Index: 5762181 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.5977. Min Act: -0.1700
Data Index: 2235155 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.5977. Min Act: -0.1700
Data Index: 1149286 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.5977. Min Act: -0.1700
Data Index: 1390449 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.5977. Min Act: -0.1700
Data Index: 4549293 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6602. Min Range: -12.6602
Max Act: 11.5977. Min Act: -0.1700
Data Index: 508865 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19