Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2107 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5611. Min Range: -5.5611
Max Act: 5.5611. Min Act: -0.1700
Data Index: 6396284 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5611. Min Range: -5.5611
Max Act: 5.3736. Min Act: -0.1700
Data Index: 1774231 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5611. Min Range: -5.5611
Max Act: 5.1861. Min Act: -0.1700
Data Index: 5551367 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5611. Min Range: -5.5611
Max Act: 5.0298. Min Act: -0.1700
Data Index: 5705116 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5611. Min Range: -5.5611
Max Act: 5.0298. Min Act: -0.1700
Data Index: 5575221 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9986. Min Act: -0.1700
Data Index: 7277859 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9986. Min Act: -0.1700
Data Index: 5524740 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9986. Min Act: -0.1700
Data Index: 8419511 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9673. Min Act: -0.1700
Data Index: 2662699 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9673. Min Act: -0.1700
Data Index: 6846375 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9673. Min Act: -0.1700
Data Index: 5065840 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9673. Min Act: -0.1700
Data Index: 2852043 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9673. Min Act: -0.1700
Data Index: 2550461 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9673. Min Act: -0.1700
Data Index: 4293550 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9673. Min Act: -0.1700
Data Index: 7576164 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9048. Min Act: -0.1700
Data Index: 3314162 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9361. Min Act: -0.1700
Data Index: 4611832 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9361. Min Act: -0.1700
Data Index: 2292054 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9048. Min Act: -0.1700
Data Index: 1492318 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5611. Min Range: -5.5611
Max Act: 4.9361. Min Act: -0.1700
Data Index: 5837501 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19