Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0537. Min Range: -5.0537
Max Act: 5.0537. Min Act: -0.1700
Data Index: 3623410 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.8350. Min Act: -0.1700
Data Index: 4101500 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.8037. Min Act: -0.1700
Data Index: 4858406 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.7100. Min Act: -0.1700
Data Index: 8629718 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.6475. Min Act: -0.1700
Data Index: 8504480 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.6162. Min Act: -0.1700
Data Index: 5859560 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.6162. Min Act: -0.1700
Data Index: 7181981 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.6475. Min Act: -0.1700
Data Index: 5261538 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.5850. Min Act: -0.1700
Data Index: 5268031 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.5850. Min Act: -0.1700
Data Index: 8629719 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.5850. Min Act: -0.1700
Data Index: 7185932 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.5537. Min Act: -0.1700
Data Index: 1986155 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.5537. Min Act: -0.1700
Data Index: 8299961 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.5537. Min Act: -0.1700
Data Index: 7885471 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.5225. Min Act: -0.1700
Data Index: 5144389 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.5225. Min Act: -0.1700
Data Index: 8556566 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.5225. Min Act: -0.1700
Data Index: 1979479 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.4912. Min Act: -0.1700
Data Index: 240934 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.4912. Min Act: -0.1700
Data Index: 3623409 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0537. Min Range: -5.0537
Max Act: 4.4912. Min Act: -0.1700
Data Index: 5346331 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19