Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.7311. Min Act: -0.1700
Data Index: 456759 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.7311. Min Act: -0.1700
Data Index: 1541159 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.6373. Min Act: -0.1700
Data Index: 6549801 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.6373. Min Act: -0.1700
Data Index: 4430841 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.6061. Min Act: -0.1700
Data Index: 6028483 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.5748. Min Act: -0.1700
Data Index: 276646 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.5436. Min Act: -0.1700
Data Index: 1263854 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.5748. Min Act: -0.1700
Data Index: 5782669 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.5436. Min Act: -0.1700
Data Index: 4779373 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.6061. Min Act: -0.1700
Data Index: 2196704 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.5436. Min Act: -0.1700
Data Index: 4344937 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.5436. Min Act: -0.1700
Data Index: 3679302 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.5436. Min Act: -0.1700
Data Index: 3442610 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.4811. Min Act: -0.1700
Data Index: 1586119 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.4811. Min Act: -0.1700
Data Index: 5598441 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.4498. Min Act: -0.1700
Data Index: 5863148 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.3873. Min Act: -0.1700
Data Index: 2036060 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.4186. Min Act: -0.1700
Data Index: 6526584 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.3873. Min Act: -0.1700
Data Index: 314194 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7311. Min Range: -4.7311
Max Act: 4.4186. Min Act: -0.1700
Data Index: 438772 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19