Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 612 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1881. Min Range: -8.1881
Max Act: 8.1881. Min Act: -0.1700
Data Index: 8305151 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1881. Min Range: -8.1881
Max Act: 8.1256. Min Act: -0.1700
Data Index: 1214773 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1881. Min Range: -8.1881
Max Act: 8.1256. Min Act: -0.1700
Data Index: 5052458 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.8756. Min Act: -0.1700
Data Index: 6781873 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.8756. Min Act: -0.1700
Data Index: 4803962 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.8131. Min Act: -0.1700
Data Index: 3053335 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.7819. Min Act: -0.1700
Data Index: 4419456 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.7194. Min Act: -0.1700
Data Index: 2019860 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.6569. Min Act: -0.1700
Data Index: 5048090 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.5944. Min Act: -0.1700
Data Index: 3010429 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.5944. Min Act: -0.1700
Data Index: 7435043 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.5319. Min Act: -0.1700
Data Index: 8713054 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.5006. Min Act: -0.1700
Data Index: 134794 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.4694. Min Act: -0.1700
Data Index: 7717339 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.4381. Min Act: -0.1700
Data Index: 6681816 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.4069. Min Act: -0.1700
Data Index: 4328267 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.3756. Min Act: -0.1700
Data Index: 2672591 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.4069. Min Act: -0.1700
Data Index: 3768143 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.4069. Min Act: -0.1700
Data Index: 1365657 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1881. Min Range: -8.1881
Max Act: 7.3756. Min Act: -0.1700
Data Index: 7134517 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19