Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6279 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0338. Min Range: -2.0338
Max Act: 2.0338. Min Act: -0.1700
Data Index: 7807368 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.9831. Min Act: -0.1699
Data Index: 60118 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.9831. Min Act: -0.1700
Data Index: 8464589 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.9662. Min Act: -0.1700
Data Index: 5580193 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.9492. Min Act: -0.1700
Data Index: 3757994 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.9662. Min Act: -0.1700
Data Index: 603689 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8982. Min Act: -0.1700
Data Index: 5869930 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8982. Min Act: -0.1700
Data Index: 1980978 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8640. Min Act: -0.1700
Data Index: 2254051 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8640. Min Act: -0.1700
Data Index: 6716575 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8640. Min Act: -0.1700
Data Index: 7362647 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8640. Min Act: -0.1700
Data Index: 1177929 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8469. Min Act: -0.1700
Data Index: 2629950 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8469. Min Act: -0.1700
Data Index: 6064412 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8297. Min Act: -0.1700
Data Index: 406352 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8469. Min Act: -0.1700
Data Index: 8809203 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8297. Min Act: -0.1700
Data Index: 6140184 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8126. Min Act: -0.1700
Data Index: 4612484 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.7954. Min Act: -0.1700
Data Index: 8116162 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0338. Min Range: -2.0338
Max Act: 1.8126. Min Act: -0.1700
Data Index: 4856712 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19