Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1926. Min Range: -7.1926
Max Act: 7.1926. Min Act: -0.1700
Data Index: 8665655 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1926. Min Range: -7.1926
Max Act: 7.1301. Min Act: -0.1700
Data Index: 6121193 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.9426. Min Act: -0.1700
Data Index: 4008875 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.8488. Min Act: -0.1700
Data Index: 2702971 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.8176. Min Act: -0.1700
Data Index: 337071 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.7551. Min Act: -0.1700
Data Index: 6841891 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.6301. Min Act: -0.1700
Data Index: 7696067 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.6613. Min Act: -0.1700
Data Index: 6025454 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.6613. Min Act: -0.1700
Data Index: 7810117 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.6301. Min Act: -0.1700
Data Index: 7609423 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.5988. Min Act: -0.1700
Data Index: 6352813 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.5363. Min Act: -0.1700
Data Index: 7880534 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.5363. Min Act: -0.1700
Data Index: 2178310 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.5051. Min Act: -0.1700
Data Index: 1076243 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.4738. Min Act: -0.1700
Data Index: 1640199 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.4426. Min Act: -0.1700
Data Index: 562983 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.5051. Min Act: -0.1700
Data Index: 353863 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.4113. Min Act: -0.1700
Data Index: 6682496 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.4426. Min Act: -0.1700
Data Index: 1791596 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1926. Min Range: -7.1926
Max Act: 6.4426. Min Act: -0.1700
Data Index: 6381491 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19