Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 828 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 9.1077. Min Range: -9.1077
Max Act: 7.4202. Min Act: -0.1700
Data Index: 2039599 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.6702. Min Act: -0.1698
Data Index: 7357563 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1077. Min Range: -9.1077
Max Act: 9.1077. Min Act: -0.1699
Data Index: 2339487 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.9827. Min Act: -0.1700
Data Index: 3227828 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1077. Min Range: -9.1077
Max Act: 9.0452. Min Act: -0.1699
Data Index: 3227826 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.8577. Min Act: -0.1700
Data Index: 3227831 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.7952. Min Act: -0.1700
Data Index: 2339488 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.7952. Min Act: -0.1700
Data Index: 5028838 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.6077. Min Act: -0.1700
Data Index: 2339486 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.6077. Min Act: -0.1700
Data Index: 3227827 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.9202. Min Act: -0.1700
Data Index: 6817743 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.1702. Min Act: -0.1700
Data Index: 6817746 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.2952. Min Act: -0.1700
Data Index: 5028836 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.1702. Min Act: -0.1697
Data Index: 3227819 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.4202. Min Act: -0.1682
Data Index: 187527 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.2952. Min Act: -0.1695
Data Index: 6437405 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.1702. Min Act: -0.1699
Data Index: 2934108 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1077. Min Range: -9.1077
Max Act: 8.1702. Min Act: -0.1700
Data Index: 1788906 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1077. Min Range: -9.1077
Max Act: 7.9827. Min Act: -0.1698
Data Index: 6460359 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1077. Min Range: -9.1077
Max Act: 7.6077. Min Act: -0.1622
Data Index: 8701707 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19