Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3655 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.1789. Min Act: -0.1700
Data Index: 2749835 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.1476. Min Act: -0.1700
Data Index: 2642670 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0851. Min Act: -0.1700
Data Index: 5017112 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0226. Min Act: -0.1700
Data Index: 5824692 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0226. Min Act: -0.1700
Data Index: 7762054 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0226. Min Act: -0.1700
Data Index: 3406042 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0539. Min Act: -0.1700
Data Index: 6085491 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0226. Min Act: -0.1700
Data Index: 2026453 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0226. Min Act: -0.1700
Data Index: 4363515 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0226. Min Act: -0.1700
Data Index: 7494855 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0539. Min Act: -0.1700
Data Index: 4037554 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9914. Min Act: -0.1700
Data Index: 3336969 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9914. Min Act: -0.1700
Data Index: 929259 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9914. Min Act: -0.1700
Data Index: 4326419 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9914. Min Act: -0.1700
Data Index: 3192206 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9601. Min Act: -0.1700
Data Index: 8302066 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9601. Min Act: -0.1700
Data Index: 4168389 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9914. Min Act: -0.1700
Data Index: 1521121 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9601. Min Act: -0.1700
Data Index: 2065964 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9601. Min Act: -0.1700
Data Index: 3890349 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19