Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4019 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.5583. Min Act: -0.1700
Data Index: 1481861 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.3797. Min Act: -0.1700
Data Index: 4321802 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.3633. Min Act: -0.1700
Data Index: 6159337 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.3305. Min Act: -0.1700
Data Index: 6677399 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.3469. Min Act: -0.1700
Data Index: 8147783 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.3469. Min Act: -0.1700
Data Index: 3011895 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.2977. Min Act: -0.1700
Data Index: 6416921 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.2977. Min Act: -0.1700
Data Index: 4467855 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.2812. Min Act: -0.1700
Data Index: 8807099 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.2647. Min Act: -0.1700
Data Index: 8315811 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.2317. Min Act: -0.1700
Data Index: 7113926 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.2482. Min Act: -0.1700
Data Index: 7994210 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.2151. Min Act: -0.1700
Data Index: 5004993 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.1985. Min Act: -0.1700
Data Index: 4474905 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.1985. Min Act: -0.1700
Data Index: 7418067 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.1819. Min Act: -0.1700
Data Index: 1580031 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.1819. Min Act: -0.1700
Data Index: 4203988 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.1819. Min Act: -0.1700
Data Index: 7906958 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.1653. Min Act: -0.1700
Data Index: 956256 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5583. Min Range: -2.5583
Max Act: 2.1653. Min Act: -0.1700
Data Index: 1822124 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19