Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1670 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0447. Min Range: -5.0447
Max Act: 5.0447. Min Act: -0.1700
Data Index: 8747014 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.9510. Min Act: -0.1700
Data Index: 1669226 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.8885. Min Act: -0.1700
Data Index: 2267489 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.7947. Min Act: -0.1700
Data Index: 5858253 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.7947. Min Act: -0.1700
Data Index: 8813153 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.7010. Min Act: -0.1700
Data Index: 420964 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.6697. Min Act: -0.1700
Data Index: 1320326 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.6072. Min Act: -0.1700
Data Index: 2489581 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.5447. Min Act: -0.1700
Data Index: 1523706 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.5760. Min Act: -0.1700
Data Index: 8030922 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.5760. Min Act: -0.1700
Data Index: 3626242 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.5760. Min Act: -0.1700
Data Index: 2033463 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.5760. Min Act: -0.1700
Data Index: 5678033 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.5760. Min Act: -0.1700
Data Index: 5910073 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.5135. Min Act: -0.1700
Data Index: 6422593 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.4822. Min Act: -0.1700
Data Index: 697250 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.5135. Min Act: -0.1700
Data Index: 3816476 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.4822. Min Act: -0.1700
Data Index: 615701 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.4822. Min Act: -0.1700
Data Index: 3255154 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0447. Min Range: -5.0447
Max Act: 4.4822. Min Act: -0.1700
Data Index: 5424977 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19