Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1266 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7047. Min Range: -7.7047
Max Act: 7.7047. Min Act: -0.1700
Data Index: 2044403 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7047. Min Range: -7.7047
Max Act: 7.1734. Min Act: -0.1700
Data Index: 6031428 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7047. Min Range: -7.7047
Max Act: 7.1734. Min Act: -0.1700
Data Index: 7295860 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7047. Min Range: -7.7047
Max Act: 7.1109. Min Act: -0.1700
Data Index: 7640542 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7047. Min Range: -7.7047
Max Act: 7.0797. Min Act: -0.1700
Data Index: 556710 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7047. Min Range: -7.7047
Max Act: 7.0172. Min Act: -0.1700
Data Index: 4820428 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7047. Min Range: -7.7047
Max Act: 7.0172. Min Act: -0.1700
Data Index: 3108129 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.9859. Min Act: -0.1700
Data Index: 3784913 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.9859. Min Act: -0.1700
Data Index: 6212696 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.9547. Min Act: -0.1700
Data Index: 4850554 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.8922. Min Act: -0.1700
Data Index: 3323652 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.8922. Min Act: -0.1700
Data Index: 5520595 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.8609. Min Act: -0.1700
Data Index: 8353678 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.8297. Min Act: -0.1700
Data Index: 891074 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.7672. Min Act: -0.1700
Data Index: 4436551 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.7672. Min Act: -0.1700
Data Index: 756573 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.7672. Min Act: -0.1700
Data Index: 5903169 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.7359. Min Act: -0.1700
Data Index: 5126322 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.7047. Min Act: -0.1700
Data Index: 6969545 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7047. Min Range: -7.7047
Max Act: 6.7047. Min Act: -0.1700
Data Index: 4565722 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19