Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2543. Min Range: -8.2543
Max Act: 8.2543. Min Act: -0.1700
Data Index: 3700094 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.9730. Min Act: -0.1700
Data Index: 7181579 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.8793. Min Act: -0.1700
Data Index: 8008821 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.7543. Min Act: -0.1700
Data Index: 1316707 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.6293. Min Act: -0.1700
Data Index: 1253349 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.5668. Min Act: -0.1700
Data Index: 73869 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.5355. Min Act: -0.1700
Data Index: 8718975 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.5355. Min Act: -0.1700
Data Index: 3574464 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.5355. Min Act: -0.1700
Data Index: 6942831 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.5043. Min Act: -0.1700
Data Index: 3667257 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.5043. Min Act: -0.1700
Data Index: 7979353 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.5043. Min Act: -0.1700
Data Index: 4987331 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.4418. Min Act: -0.1700
Data Index: 1230807 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.4730. Min Act: -0.1700
Data Index: 403764 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.4105. Min Act: -0.1700
Data Index: 5266984 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.4105. Min Act: -0.1700
Data Index: 2510161 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.3793. Min Act: -0.1700
Data Index: 6541530 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.4105. Min Act: -0.1700
Data Index: 6428744 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.3480. Min Act: -0.1700
Data Index: 2455093 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2543. Min Range: -8.2543
Max Act: 7.3480. Min Act: -0.1700
Data Index: 689820 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19