Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 312 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.7189. Min Act: -0.1700
Data Index: 3306425 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.7502. Min Act: -0.1700
Data Index: 4385746 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.6877. Min Act: -0.1700
Data Index: 730112 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.7189. Min Act: -0.1700
Data Index: 6533552 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.7189. Min Act: -0.1700
Data Index: 5064519 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.7502. Min Act: -0.1700
Data Index: 5973129 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.6877. Min Act: -0.1700
Data Index: 2565148 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.6564. Min Act: -0.1700
Data Index: 411848 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.6564. Min Act: -0.1700
Data Index: 7026509 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.6564. Min Act: -0.1700
Data Index: 1666219 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.6564. Min Act: -0.1700
Data Index: 1233628 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.6564. Min Act: -0.1700
Data Index: 2523211 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.6252. Min Act: -0.1700
Data Index: 2087298 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.6252. Min Act: -0.1700
Data Index: 7180776 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.5939. Min Act: -0.1700
Data Index: 8718407 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.5627. Min Act: -0.1700
Data Index: 3399516 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.5939. Min Act: -0.1700
Data Index: 186738 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.5939. Min Act: -0.1700
Data Index: 4950386 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.5939. Min Act: -0.1700
Data Index: 3863336 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7502. Min Range: -5.7502
Max Act: 5.5939. Min Act: -0.1700
Data Index: 2271580 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19