Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1427 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.6616. Min Act: -0.1700
Data Index: 4453679 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.6147. Min Act: -0.1700
Data Index: 2089282 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5834. Min Act: -0.1700
Data Index: 5663356 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5521. Min Act: -0.1700
Data Index: 4868540 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5364. Min Act: -0.1700
Data Index: 2827200 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5364. Min Act: -0.1700
Data Index: 7551872 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4894. Min Act: -0.1700
Data Index: 8710268 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5207. Min Act: -0.1700
Data Index: 5387090 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5051. Min Act: -0.1700
Data Index: 5543172 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4581. Min Act: -0.1700
Data Index: 371251 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4581. Min Act: -0.1700
Data Index: 7135618 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4581. Min Act: -0.1700
Data Index: 7981936 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4267. Min Act: -0.1700
Data Index: 4547897 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4424. Min Act: -0.1700
Data Index: 4887879 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4424. Min Act: -0.1700
Data Index: 6373073 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4267. Min Act: -0.1700
Data Index: 343067 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4267. Min Act: -0.1700
Data Index: 6696246 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4738. Min Act: -0.1700
Data Index: 4000226 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4267. Min Act: -0.1700
Data Index: 5865092 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4111. Min Act: -0.1700
Data Index: 1818395 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19