Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1328 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.6760. Min Act: -0.1700
Data Index: 965003 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.5822. Min Act: -0.1700
Data Index: 1299158 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.5197. Min Act: -0.1700
Data Index: 495604 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.4572. Min Act: -0.1700
Data Index: 1280562 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.4572. Min Act: -0.1700
Data Index: 1505742 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.4572. Min Act: -0.1700
Data Index: 8065364 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.4572. Min Act: -0.1700
Data Index: 7925036 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.4572. Min Act: -0.1700
Data Index: 4959106 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.4260. Min Act: -0.1700
Data Index: 3870389 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.4885. Min Act: -0.1700
Data Index: 2813642 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.4260. Min Act: -0.1700
Data Index: 4174496 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.4260. Min Act: -0.1700
Data Index: 2944388 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.4572. Min Act: -0.1700
Data Index: 8300520 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.4572. Min Act: -0.1700
Data Index: 811544 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.3635. Min Act: -0.1700
Data Index: 4457097 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.3947. Min Act: -0.1700
Data Index: 7833544 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.3947. Min Act: -0.1700
Data Index: 5624065 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.3947. Min Act: -0.1700
Data Index: 7418310 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.4260. Min Act: -0.1700
Data Index: 3810565 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6760. Min Range: -4.6760
Max Act: 4.3322. Min Act: -0.1700
Data Index: 2141177 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19