Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2698 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.2029. Min Act: -0.1700
Data Index: 1676385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.2029. Min Act: -0.1700
Data Index: 3295248 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 4241225 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 3667248 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 3461853 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 3255026 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 7569814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 7452912 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 7165538 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 7165502 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 5694667 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 5322494 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 5205573 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 56405 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 1654186 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 687844 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 4906829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 1510402 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0779. Min Act: -0.1700
Data Index: 1155703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.0154. Min Act: -0.1700
Data Index: 3704284 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19