Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2767 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 21.1253. Min Range: -21.1253
Max Act: 21.1253. Min Act: -0.1700
Data Index: 1148472 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 21.1253. Min Range: -21.1253
Max Act: 20.8753. Min Act: -0.1700
Data Index: 1099175 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 21.1253. Min Range: -21.1253
Max Act: 20.7503. Min Act: -0.1700
Data Index: 7256016 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 21.1253. Min Range: -21.1253
Max Act: 20.8753. Min Act: -0.1700
Data Index: 6679083 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 21.1253. Min Range: -21.1253
Max Act: 20.6253. Min Act: -0.1700
Data Index: 578913 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 21.1253. Min Range: -21.1253
Max Act: 20.2503. Min Act: -0.1700
Data Index: 4287928 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 21.1253. Min Range: -21.1253
Max Act: 20.2503. Min Act: -0.1700
Data Index: 1398070 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 21.1253. Min Range: -21.1253
Max Act: 20.2503. Min Act: -0.1700
Data Index: 1538898 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 21.1253. Min Range: -21.1253
Max Act: 20.2503. Min Act: -0.1700
Data Index: 3281329 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 21.1253. Min Range: -21.1253
Max Act: 20.1253. Min Act: -0.1700
Data Index: 8679679 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 21.1253. Min Range: -21.1253
Max Act: 20.0003. Min Act: -0.1700
Data Index: 2137435 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 21.1253. Min Range: -21.1253
Max Act: 20.1253. Min Act: -0.1700
Data Index: 5312437 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 21.1253. Min Range: -21.1253
Max Act: 19.8753. Min Act: -0.1700
Data Index: 6061352 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 21.1253. Min Range: -21.1253
Max Act: 19.8753. Min Act: -0.1700
Data Index: 8585697 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 21.1253. Min Range: -21.1253
Max Act: 19.8753. Min Act: -0.1700
Data Index: 6457972 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 21.1253. Min Range: -21.1253
Max Act: 20.0003. Min Act: -0.1700
Data Index: 6923650 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 21.1253. Min Range: -21.1253
Max Act: 19.7503. Min Act: -0.1700
Data Index: 8316884 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 21.1253. Min Range: -21.1253
Max Act: 19.8753. Min Act: -0.1700
Data Index: 5893834 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 21.1253. Min Range: -21.1253
Max Act: 19.6253. Min Act: -0.1700
Data Index: 3205470 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 21.1253. Min Range: -21.1253
Max Act: 19.7503. Min Act: -0.1700
Data Index: 2137424 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19