Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 11 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2287. Min Range: -5.2287
Max Act: 5.2287. Min Act: -0.1700
Data Index: 6024204 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2287. Min Range: -5.2287
Max Act: 5.1662. Min Act: -0.1700
Data Index: 429334 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2287. Min Range: -5.2287
Max Act: 5.1037. Min Act: -0.1700
Data Index: 4800805 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2287. Min Range: -5.2287
Max Act: 5.1037. Min Act: -0.1700
Data Index: 5814598 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2287. Min Range: -5.2287
Max Act: 5.0724. Min Act: -0.1700
Data Index: 1262834 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2287. Min Range: -5.2287
Max Act: 5.0412. Min Act: -0.1700
Data Index: 5315833 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.9787. Min Act: -0.1700
Data Index: 3031070 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.9162. Min Act: -0.1700
Data Index: 8561172 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.9474. Min Act: -0.1700
Data Index: 2660547 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.8849. Min Act: -0.1700
Data Index: 156363 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.9162. Min Act: -0.1700
Data Index: 5870996 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.8849. Min Act: -0.1700
Data Index: 6471951 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.8537. Min Act: -0.1700
Data Index: 589487 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.8537. Min Act: -0.1700
Data Index: 5719776 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.8849. Min Act: -0.1700
Data Index: 7374213 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.8537. Min Act: -0.1700
Data Index: 7539129 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.8849. Min Act: -0.1700
Data Index: 995866 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.8537. Min Act: -0.1700
Data Index: 384999 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.8537. Min Act: -0.1700
Data Index: 3937469 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2287. Min Range: -5.2287
Max Act: 4.8537. Min Act: -0.1700
Data Index: 4855847 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19