Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.7873. Min Act: -0.1700
Data Index: 1330010 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.6311. Min Act: -0.1700
Data Index: 3296949 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.6311. Min Act: -0.1700
Data Index: 7675468 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.5998. Min Act: -0.1700
Data Index: 1638925 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.5686. Min Act: -0.1700
Data Index: 2162075 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.5061. Min Act: -0.1700
Data Index: 98715 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.5373. Min Act: -0.1700
Data Index: 2162072 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.5373. Min Act: -0.1700
Data Index: 4811959 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.5061. Min Act: -0.1700
Data Index: 910698 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.5061. Min Act: -0.1700
Data Index: 1795849 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.5061. Min Act: -0.1700
Data Index: 7907647 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.4436. Min Act: -0.1700
Data Index: 1128797 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.4436. Min Act: -0.1700
Data Index: 3269646 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.4123. Min Act: -0.1700
Data Index: 1419849 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.4123. Min Act: -0.1700
Data Index: 5728310 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.3811. Min Act: -0.1700
Data Index: 6033239 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.4123. Min Act: -0.1700
Data Index: 6087781 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.3498. Min Act: -0.1700
Data Index: 4001255 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.3498. Min Act: -0.1700
Data Index: 803803 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7873. Min Range: -4.7873
Max Act: 4.3498. Min Act: -0.1700
Data Index: 3069219 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19