Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3135 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.8934. Min Act: -0.1692
Data Index: 7992965 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.8593. Min Act: -0.1658
Data Index: 4881547 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.8593. Min Act: -0.1495
Data Index: 5390717 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7906. Min Act: -0.1681
Data Index: 5259027 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7906. Min Act: -0.1673
Data Index: 2201569 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7906. Min Act: -0.1679
Data Index: 8824152 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7734. Min Act: -0.1675
Data Index: 8438141 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7647. Min Act: -0.1700
Data Index: 3393657 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7475. Min Act: -0.1696
Data Index: 2056415 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7906. Min Act: -0.1699
Data Index: 6451601 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7647. Min Act: -0.1655
Data Index: 1125389 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7561. Min Act: -0.1645
Data Index: 8605812 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7561. Min Act: -0.1606
Data Index: 5036277 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7302. Min Act: -0.1700
Data Index: 7107996 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7388. Min Act: -0.1687
Data Index: 89169 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7388. Min Act: -0.1700
Data Index: 8605784 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7215. Min Act: -0.1666
Data Index: 4102135 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7388. Min Act: -0.1555
Data Index: 6451598 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7302. Min Act: -0.1698
Data Index: 2407860 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8934. Min Range: -1.8934
Max Act: 1.7129. Min Act: -0.1700
Data Index: 8405563 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19