Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1539. Min Act: -0.1700
Data Index: 3432717 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.8727. Min Act: -0.1699
Data Index: 3658696 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.8414. Min Act: -0.1700
Data Index: 3430947 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.8102. Min Act: -0.1700
Data Index: 8665571 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.8102. Min Act: -0.1700
Data Index: 1824748 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.7789. Min Act: -0.1700
Data Index: 3008565 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.7789. Min Act: -0.1700
Data Index: 7374194 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.7789. Min Act: -0.1700
Data Index: 2958495 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.7477. Min Act: -0.1700
Data Index: 6883026 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.7789. Min Act: -0.1700
Data Index: 4563281 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.7477. Min Act: -0.1700
Data Index: 5182190 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.7789. Min Act: -0.1700
Data Index: 4492423 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.7164. Min Act: -0.1700
Data Index: 5283245 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.7164. Min Act: -0.1700
Data Index: 4746147 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.7164. Min Act: -0.1700
Data Index: 7297519 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.7164. Min Act: -0.1700
Data Index: 6964854 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.6852. Min Act: -0.1700
Data Index: 6470647 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.6852. Min Act: -0.1700
Data Index: 8689764 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.6852. Min Act: -0.1700
Data Index: 3861069 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1539. Min Range: -5.1539
Max Act: 4.6852. Min Act: -0.1700
Data Index: 1668871 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19