Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2106 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0587. Min Range: -2.0587
Max Act: 2.0587. Min Act: -0.1700
Data Index: 6898261 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.9574. Min Act: -0.1700
Data Index: 1605852 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.9574. Min Act: -0.1700
Data Index: 4608625 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.9404. Min Act: -0.1700
Data Index: 224389 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.9234. Min Act: -0.1700
Data Index: 8126458 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.8551. Min Act: -0.1700
Data Index: 64518 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.8380. Min Act: -0.1700
Data Index: 4630734 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.8208. Min Act: -0.1700
Data Index: 4823433 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.8122. Min Act: -0.1700
Data Index: 1166331 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.8122. Min Act: -0.1700
Data Index: 1378314 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.8036. Min Act: -0.1700
Data Index: 4907763 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.8036. Min Act: -0.1700
Data Index: 6909342 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.7950. Min Act: -0.1700
Data Index: 2268883 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.7950. Min Act: -0.1700
Data Index: 7619634 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.7864. Min Act: -0.1700
Data Index: 2925479 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.8036. Min Act: -0.1700
Data Index: 4579854 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.8036. Min Act: -0.1700
Data Index: 4727889 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.7778. Min Act: -0.1700
Data Index: 2438809 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.7864. Min Act: -0.1700
Data Index: 4600577 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0587. Min Range: -2.0587
Max Act: 1.7692. Min Act: -0.1700
Data Index: 5332834 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19