Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1874 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5674. Min Range: -7.5674
Max Act: 7.5674. Min Act: -0.1700
Data Index: 3414912 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5674. Min Range: -7.5674
Max Act: 7.3799. Min Act: -0.1700
Data Index: 3414914 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5674. Min Range: -7.5674
Max Act: 7.1299. Min Act: -0.1700
Data Index: 47512 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5674. Min Range: -7.5674
Max Act: 7.1611. Min Act: -0.1700
Data Index: 1540120 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5674. Min Range: -7.5674
Max Act: 7.0049. Min Act: -0.1700
Data Index: 7741856 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.9424. Min Act: -0.1700
Data Index: 3244685 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.9736. Min Act: -0.1700
Data Index: 4784932 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.9736. Min Act: -0.1700
Data Index: 1307944 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.8799. Min Act: -0.1700
Data Index: 618866 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.7861. Min Act: -0.1700
Data Index: 7064149 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.8799. Min Act: -0.1700
Data Index: 1794806 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.7861. Min Act: -0.1700
Data Index: 3709731 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.8174. Min Act: -0.1700
Data Index: 2976464 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.7549. Min Act: -0.1700
Data Index: 639755 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.7236. Min Act: -0.1700
Data Index: 7358382 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.6924. Min Act: -0.1700
Data Index: 7358388 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.8174. Min Act: -0.1700
Data Index: 6739348 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.7549. Min Act: -0.1700
Data Index: 6753016 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.6924. Min Act: -0.1700
Data Index: 2662908 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5674. Min Range: -7.5674
Max Act: 6.6299. Min Act: -0.1700
Data Index: 60466 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19