Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2200 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.9452. Min Act: -0.1700
Data Index: 5984478 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.8827. Min Act: -0.1700
Data Index: 1112018 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.8827. Min Act: -0.1700
Data Index: 6337618 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.8827. Min Act: -0.1700
Data Index: 4550412 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.8514. Min Act: -0.1700
Data Index: 4663271 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.8514. Min Act: -0.1700
Data Index: 1920584 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.8827. Min Act: -0.1700
Data Index: 332418 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.8514. Min Act: -0.1700
Data Index: 6602775 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.8358. Min Act: -0.1700
Data Index: 992958 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.8514. Min Act: -0.1700
Data Index: 170126 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.7889. Min Act: -0.1700
Data Index: 62543 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.7732. Min Act: -0.1700
Data Index: 3642131 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.7732. Min Act: -0.1700
Data Index: 8441547 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.7889. Min Act: -0.1700
Data Index: 4181346 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.8201. Min Act: -0.1700
Data Index: 7160312 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.7576. Min Act: -0.1700
Data Index: 3789794 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.7576. Min Act: -0.1700
Data Index: 4248798 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.7889. Min Act: -0.1700
Data Index: 5055107 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.7107. Min Act: -0.1700
Data Index: 7160324 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9452. Min Range: -3.9452
Max Act: 3.7576. Min Act: -0.1700
Data Index: 47081 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19