Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1650 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0797. Min Range: -5.0797
Max Act: 5.0797. Min Act: -0.1700
Data Index: 1533279 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.7985. Min Act: -0.1700
Data Index: 4826102 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.7047. Min Act: -0.1700
Data Index: 4928419 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.6735. Min Act: -0.1700
Data Index: 3537814 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.6422. Min Act: -0.1700
Data Index: 4365777 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.6422. Min Act: -0.1700
Data Index: 165101 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.6422. Min Act: -0.1700
Data Index: 6819134 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.6422. Min Act: -0.1700
Data Index: 15019 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.6422. Min Act: -0.1700
Data Index: 6455799 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.6422. Min Act: -0.1700
Data Index: 6945188 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.6422. Min Act: -0.1700
Data Index: 2348372 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.6110. Min Act: -0.1700
Data Index: 3080722 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.6110. Min Act: -0.1700
Data Index: 2347968 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.5797. Min Act: -0.1700
Data Index: 4928418 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.5485. Min Act: -0.1700
Data Index: 5711584 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.5485. Min Act: -0.1700
Data Index: 8802984 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.5172. Min Act: -0.1700
Data Index: 3521771 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.5172. Min Act: -0.1700
Data Index: 1606564 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.4860. Min Act: -0.1700
Data Index: 283359 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0797. Min Range: -5.0797
Max Act: 4.4860. Min Act: -0.1700
Data Index: 603913 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19