Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.5251. Min Range: -11.5251
Max Act: 11.5251. Min Act: -0.1700
Data Index: 6459071 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5251. Min Range: -11.5251
Max Act: 11.4001. Min Act: -0.1700
Data Index: 3970133 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.6501. Min Act: -0.1700
Data Index: 3970137 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.5876. Min Act: -0.1700
Data Index: 3418618 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.5876. Min Act: -0.1700
Data Index: 3215408 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.4626. Min Act: -0.1700
Data Index: 306899 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.3376. Min Act: -0.1700
Data Index: 3970132 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.3376. Min Act: -0.1700
Data Index: 3970129 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.4001. Min Act: -0.1700
Data Index: 4464085 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.2126. Min Act: -0.1700
Data Index: 7938205 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.2126. Min Act: -0.1700
Data Index: 8253364 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.1501. Min Act: -0.1700
Data Index: 3923999 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.1501. Min Act: -0.1700
Data Index: 7150602 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.1501. Min Act: -0.1700
Data Index: 3351689 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.0876. Min Act: -0.1700
Data Index: 8010561 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.0876. Min Act: -0.1700
Data Index: 2404175 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.0251. Min Act: -0.1700
Data Index: 4383103 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.0876. Min Act: -0.1700
Data Index: 4383100 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.0876. Min Act: -0.1700
Data Index: 1337569 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5251. Min Range: -11.5251
Max Act: 10.0876. Min Act: -0.1700
Data Index: 1970633 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19