Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1412 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.9138. Min Act: -0.1700
Data Index: 4796800 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.8826. Min Act: -0.1700
Data Index: 2568630 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.8669. Min Act: -0.1700
Data Index: 3547822 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.8669. Min Act: -0.1700
Data Index: 1057028 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.8200. Min Act: -0.1700
Data Index: 590915 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.8357. Min Act: -0.1700
Data Index: 5567482 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.8357. Min Act: -0.1700
Data Index: 8689822 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.8200. Min Act: -0.1700
Data Index: 5296886 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.8200. Min Act: -0.1700
Data Index: 3794721 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.7888. Min Act: -0.1700
Data Index: 7441055 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.7731. Min Act: -0.1700
Data Index: 4009965 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.7731. Min Act: -0.1700
Data Index: 7288050 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.7575. Min Act: -0.1700
Data Index: 3532708 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.7888. Min Act: -0.1700
Data Index: 8559821 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.7731. Min Act: -0.1700
Data Index: 150961 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.7575. Min Act: -0.1700
Data Index: 260801 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.7575. Min Act: -0.1700
Data Index: 2611563 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.7575. Min Act: -0.1700
Data Index: 6967398 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.7262. Min Act: -0.1700
Data Index: 7242960 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9138. Min Range: -3.9138
Max Act: 3.7419. Min Act: -0.1700
Data Index: 5290137 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19