Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 434 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.7996. Min Act: -0.1700
Data Index: 7027488 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.5184. Min Act: -0.1700
Data Index: 4085059 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.4871. Min Act: -0.1700
Data Index: 3407980 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.3309. Min Act: -0.1700
Data Index: 1583030 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.2684. Min Act: -0.1700
Data Index: 4095389 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.2684. Min Act: -0.1700
Data Index: 8720390 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.2371. Min Act: -0.1700
Data Index: 5431940 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.2371. Min Act: -0.1700
Data Index: 1919352 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.2059. Min Act: -0.1700
Data Index: 5445247 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.1746. Min Act: -0.1700
Data Index: 2607114 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.1746. Min Act: -0.1700
Data Index: 2435251 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.1121. Min Act: -0.1700
Data Index: 7058708 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.1434. Min Act: -0.1700
Data Index: 1653490 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.1434. Min Act: -0.1700
Data Index: 1838654 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.0809. Min Act: -0.1700
Data Index: 2829796 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.1121. Min Act: -0.1700
Data Index: 1335027 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.1121. Min Act: -0.1700
Data Index: 6329583 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.0809. Min Act: -0.1700
Data Index: 150284 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.0809. Min Act: -0.1700
Data Index: 7086464 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7996. Min Range: -6.7996
Max Act: 6.0184. Min Act: -0.1700
Data Index: 589296 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19