Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6351 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2004. Min Range: -9.2004
Max Act: 9.2004. Min Act: -0.1700
Data Index: 2631308 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2004. Min Range: -9.2004
Max Act: 9.0754. Min Act: -0.1700
Data Index: 4825655 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.5754. Min Act: -0.1700
Data Index: 8007278 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.5129. Min Act: -0.1700
Data Index: 2126785 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.5129. Min Act: -0.1700
Data Index: 5389310 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.4504. Min Act: -0.1700
Data Index: 7836873 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.3879. Min Act: -0.1700
Data Index: 6325616 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.2629. Min Act: -0.1700
Data Index: 5591067 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.2941. Min Act: -0.1700
Data Index: 5234363 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.2316. Min Act: -0.1700
Data Index: 8001908 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.2004. Min Act: -0.1700
Data Index: 1860322 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.2316. Min Act: -0.1700
Data Index: 5026715 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.2316. Min Act: -0.1700
Data Index: 3408357 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.1379. Min Act: -0.1700
Data Index: 4493195 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.2004. Min Act: -0.1700
Data Index: 1999249 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.1379. Min Act: -0.1700
Data Index: 7978608 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.1066. Min Act: -0.1700
Data Index: 553950 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.1066. Min Act: -0.1700
Data Index: 8202232 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.0754. Min Act: -0.1700
Data Index: 6044925 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2004. Min Range: -9.2004
Max Act: 8.0441. Min Act: -0.1700
Data Index: 6734401 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19