Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1336 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.4539. Min Act: -0.1700
Data Index: 4479811 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.3914. Min Act: -0.1700
Data Index: 7777568 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.3602. Min Act: -0.1700
Data Index: 155227 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.2977. Min Act: -0.1700
Data Index: 4751514 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.2352. Min Act: -0.1700
Data Index: 5405565 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.2039. Min Act: -0.1700
Data Index: 4751513 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.2039. Min Act: -0.1700
Data Index: 5208931 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.2039. Min Act: -0.1700
Data Index: 1449523 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.1727. Min Act: -0.1700
Data Index: 5237201 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.1414. Min Act: -0.1700
Data Index: 7924750 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.1727. Min Act: -0.1700
Data Index: 1790232 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.1414. Min Act: -0.1700
Data Index: 6932352 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.1102. Min Act: -0.1700
Data Index: 718464 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.1102. Min Act: -0.1700
Data Index: 3662416 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.1102. Min Act: -0.1700
Data Index: 2980157 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.0789. Min Act: -0.1700
Data Index: 4303961 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.0164. Min Act: -0.1700
Data Index: 4637215 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4539. Min Range: -6.4539
Max Act: 5.9852. Min Act: -0.1700
Data Index: 6788359 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4539. Min Range: -6.4539
Max Act: 6.0164. Min Act: -0.1700
Data Index: 2309510 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4539. Min Range: -6.4539
Max Act: 5.9539. Min Act: -0.1700
Data Index: 72347 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19