Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 194 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.9902. Min Act: -0.1700
Data Index: 4389665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.9589. Min Act: -0.1700
Data Index: 2702550 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.9277. Min Act: -0.1700
Data Index: 6655736 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.9589. Min Act: -0.1700
Data Index: 7168814 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.8652. Min Act: -0.1700
Data Index: 671577 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.8652. Min Act: -0.1700
Data Index: 5615260 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.8339. Min Act: -0.1700
Data Index: 5401451 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.8339. Min Act: -0.1700
Data Index: 3231581 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.8339. Min Act: -0.1700
Data Index: 4131035 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.8339. Min Act: -0.1700
Data Index: 7173017 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.8027. Min Act: -0.1700
Data Index: 5373767 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.7402. Min Act: -0.1700
Data Index: 993747 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.7402. Min Act: -0.1700
Data Index: 4526544 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.7089. Min Act: -0.1700
Data Index: 2133692 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.7402. Min Act: -0.1700
Data Index: 7499075 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.7089. Min Act: -0.1700
Data Index: 876379 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.7089. Min Act: -0.1700
Data Index: 7079299 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.6464. Min Act: -0.1700
Data Index: 5196407 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.7089. Min Act: -0.1700
Data Index: 7439488 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.6464. Min Act: -0.1700
Data Index: 4722876 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19