Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4195 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3104. Min Range: -9.3104
Max Act: 9.3104. Min Act: -0.1700
Data Index: 6706786 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3104. Min Range: -9.3104
Max Act: 9.1854. Min Act: -0.1700
Data Index: 7321838 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3104. Min Range: -9.3104
Max Act: 9.1854. Min Act: -0.1700
Data Index: 4930385 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3104. Min Range: -9.3104
Max Act: 9.0604. Min Act: -0.1700
Data Index: 7113071 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.9354. Min Act: -0.1700
Data Index: 3016354 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.8729. Min Act: -0.1700
Data Index: 3155889 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.8729. Min Act: -0.1700
Data Index: 6385754 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.8729. Min Act: -0.1700
Data Index: 2197207 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.8104. Min Act: -0.1700
Data Index: 6283573 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.7479. Min Act: -0.1700
Data Index: 5376737 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.8104. Min Act: -0.1700
Data Index: 2096876 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.8104. Min Act: -0.1700
Data Index: 8640601 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.7479. Min Act: -0.1700
Data Index: 2213434 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.7479. Min Act: -0.1700
Data Index: 5368426 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.7479. Min Act: -0.1700
Data Index: 6609512 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.6854. Min Act: -0.1700
Data Index: 2056896 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.6854. Min Act: -0.1700
Data Index: 5965703 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.6854. Min Act: -0.1700
Data Index: 1088250 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.6229. Min Act: -0.1700
Data Index: 6733679 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3104. Min Range: -9.3104
Max Act: 8.6854. Min Act: -0.1700
Data Index: 559628 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19