Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2612 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.7702. Min Act: -0.1700
Data Index: 2299094 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.7077. Min Act: -0.1700
Data Index: 2194434 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.7077. Min Act: -0.1700
Data Index: 2630138 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.6452. Min Act: -0.1700
Data Index: 1472396 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.6765. Min Act: -0.1700
Data Index: 2992858 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.6765. Min Act: -0.1700
Data Index: 6750349 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.5827. Min Act: -0.1700
Data Index: 5660787 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.6452. Min Act: -0.1700
Data Index: 4886494 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.5827. Min Act: -0.1700
Data Index: 1747973 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.5827. Min Act: -0.1700
Data Index: 6690192 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.6140. Min Act: -0.1700
Data Index: 1843452 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.5515. Min Act: -0.1700
Data Index: 87325 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.5202. Min Act: -0.1700
Data Index: 1797680 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.4577. Min Act: -0.1700
Data Index: 8620428 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.4577. Min Act: -0.1700
Data Index: 5299999 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.4577. Min Act: -0.1700
Data Index: 638335 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.4577. Min Act: -0.1700
Data Index: 4549197 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.4265. Min Act: -0.1700
Data Index: 5619992 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.4577. Min Act: -0.1700
Data Index: 1424775 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7702. Min Range: -5.7702
Max Act: 5.3640. Min Act: -0.1700
Data Index: 7134030 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19