Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3653 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.2491. Min Act: -0.1700
Data Index: 5082991 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.2326. Min Act: -0.1700
Data Index: 5877405 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0994. Min Act: -0.1700
Data Index: 4276587 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0994. Min Act: -0.1699
Data Index: 4427398 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0827. Min Act: -0.1700
Data Index: 6831185 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0827. Min Act: -0.1700
Data Index: 3837542 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0659. Min Act: -0.1700
Data Index: 6961090 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0659. Min Act: -0.1700
Data Index: 3653530 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0659. Min Act: -0.1700
Data Index: 5230039 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0491. Min Act: -0.1700
Data Index: 4176199 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0491. Min Act: -0.1700
Data Index: 2942842 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0491. Min Act: -0.1700
Data Index: 1000404 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0323. Min Act: -0.1700
Data Index: 5721692 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0323. Min Act: -0.1700
Data Index: 4113725 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0323. Min Act: -0.1700
Data Index: 5185225 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0323. Min Act: -0.1700
Data Index: 6187116 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0323. Min Act: -0.1700
Data Index: 1292658 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0154. Min Act: -0.1700
Data Index: 1534138 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0154. Min Act: -0.1700
Data Index: 6103909 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2491. Min Range: -2.2491
Max Act: 2.0154. Min Act: -0.1700
Data Index: 3234119 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19