Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1053 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0741. Min Range: -3.0741
Max Act: 3.0741. Min Act: -0.1700
Data Index: 3085925 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0741. Min Range: -3.0741
Max Act: 3.0268. Min Act: -0.1700
Data Index: 3112123 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0741. Min Range: -3.0741
Max Act: 3.0110. Min Act: -0.1700
Data Index: 8566694 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0741. Min Range: -3.0741
Max Act: 3.0110. Min Act: -0.1700
Data Index: 2280849 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0741. Min Range: -3.0741
Max Act: 3.0268. Min Act: -0.1700
Data Index: 327524 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9952. Min Act: -0.1700
Data Index: 4083041 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9952. Min Act: -0.1700
Data Index: 4126223 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9952. Min Act: -0.1700
Data Index: 8793648 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9952. Min Act: -0.1700
Data Index: 3744063 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0741. Min Range: -3.0741
Max Act: 3.0110. Min Act: -0.1700
Data Index: 4921296 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0741. Min Range: -3.0741
Max Act: 3.0110. Min Act: -0.1700
Data Index: 7045188 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9794. Min Act: -0.1700
Data Index: 1406553 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9794. Min Act: -0.1700
Data Index: 4171153 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9794. Min Act: -0.1700
Data Index: 599563 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9794. Min Act: -0.1700
Data Index: 2395401 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9794. Min Act: -0.1700
Data Index: 2573017 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9794. Min Act: -0.1700
Data Index: 152074 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9794. Min Act: -0.1700
Data Index: 4727811 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9794. Min Act: -0.1700
Data Index: 1860592 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0741. Min Range: -3.0741
Max Act: 2.9794. Min Act: -0.1700
Data Index: 5068310 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19