Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2463 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0812. Min Range: -4.0812
Max Act: 4.0812. Min Act: -0.1700
Data Index: 6880959 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0812. Min Range: -4.0812
Max Act: 4.0499. Min Act: -0.1700
Data Index: 3500497 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0812. Min Range: -4.0812
Max Act: 4.0499. Min Act: -0.1700
Data Index: 7861934 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.9874. Min Act: -0.1700
Data Index: 4355733 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.9874. Min Act: -0.1700
Data Index: 4489723 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0812. Min Range: -4.0812
Max Act: 4.0187. Min Act: -0.1700
Data Index: 5640942 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0812. Min Range: -4.0812
Max Act: 4.0187. Min Act: -0.1700
Data Index: 6426807 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.9561. Min Act: -0.1700
Data Index: 531550 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.9874. Min Act: -0.1700
Data Index: 1373699 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.9561. Min Act: -0.1700
Data Index: 8646781 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.9249. Min Act: -0.1700
Data Index: 8280051 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.9249. Min Act: -0.1700
Data Index: 1026089 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.9249. Min Act: -0.1700
Data Index: 5408156 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.9249. Min Act: -0.1700
Data Index: 3697278 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.9249. Min Act: -0.1700
Data Index: 1394014 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.9249. Min Act: -0.1700
Data Index: 1390573 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.8936. Min Act: -0.1700
Data Index: 4227265 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.8623. Min Act: -0.1700
Data Index: 4855930 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.8936. Min Act: -0.1700
Data Index: 5233618 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0812. Min Range: -4.0812
Max Act: 3.8623. Min Act: -0.1700
Data Index: 5324742 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19