Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.4452. Min Act: -0.1700
Data Index: 336296 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.4452. Min Act: -0.1700
Data Index: 8003740 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.2577. Min Act: -0.1700
Data Index: 8606906 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.2264. Min Act: -0.1700
Data Index: 5728466 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.1952. Min Act: -0.1700
Data Index: 3514347 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.1952. Min Act: -0.1700
Data Index: 6159092 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.1327. Min Act: -0.1700
Data Index: 8263900 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.0702. Min Act: -0.1700
Data Index: 2209897 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.0702. Min Act: -0.1700
Data Index: 388112 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.0389. Min Act: -0.1700
Data Index: 6671426 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.0389. Min Act: -0.1700
Data Index: 1586867 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.0389. Min Act: -0.1700
Data Index: 3936349 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.0077. Min Act: -0.1700
Data Index: 6076970 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4452. Min Range: -8.4452
Max Act: 8.0077. Min Act: -0.1700
Data Index: 1292537 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4452. Min Range: -8.4452
Max Act: 7.9452. Min Act: -0.1700
Data Index: 6450687 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4452. Min Range: -8.4452
Max Act: 7.9764. Min Act: -0.1700
Data Index: 1189586 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4452. Min Range: -8.4452
Max Act: 7.9452. Min Act: -0.1700
Data Index: 5696316 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4452. Min Range: -8.4452
Max Act: 7.9139. Min Act: -0.1700
Data Index: 4811910 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4452. Min Range: -8.4452
Max Act: 7.9139. Min Act: -0.1700
Data Index: 838695 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4452. Min Range: -8.4452
Max Act: 7.9139. Min Act: -0.1700
Data Index: 1273828 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19