Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.6056. Min Act: -0.1700
Data Index: 2445950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5411. Min Act: -0.1700
Data Index: 8207204 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5572. Min Act: -0.1700
Data Index: 1978060 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5411. Min Act: -0.1700
Data Index: 8566825 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5411. Min Act: -0.1700
Data Index: 5549947 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5411. Min Act: -0.1700
Data Index: 6199689 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5411. Min Act: -0.1700
Data Index: 7059565 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5411. Min Act: -0.1700
Data Index: 7066817 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5411. Min Act: -0.1700
Data Index: 3810682 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5249. Min Act: -0.1700
Data Index: 2442777 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5087. Min Act: -0.1700
Data Index: 3415830 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5249. Min Act: -0.1700
Data Index: 3968510 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5087. Min Act: -0.1700
Data Index: 7933937 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5087. Min Act: -0.1700
Data Index: 3198721 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5087. Min Act: -0.1700
Data Index: 3127847 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5087. Min Act: -0.1700
Data Index: 2871522 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.4925. Min Act: -0.1700
Data Index: 3996799 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5087. Min Act: -0.1700
Data Index: 7676278 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5087. Min Act: -0.1700
Data Index: 4517792 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6056. Min Range: -2.6056
Max Act: 2.5087. Min Act: -0.1700
Data Index: 250847 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19