Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.4889. Min Act: -0.1700
Data Index: 5073322 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.4361. Min Act: -0.1700
Data Index: 4478365 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.4361. Min Act: -0.1700
Data Index: 5589704 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.4273. Min Act: -0.1700
Data Index: 5270919 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.4273. Min Act: -0.1700
Data Index: 3110712 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.4185. Min Act: -0.1700
Data Index: 3701176 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.4185. Min Act: -0.1700
Data Index: 5829518 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.4097. Min Act: -0.1700
Data Index: 1170289 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.4097. Min Act: -0.1698
Data Index: 8066728 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.4009. Min Act: -0.1700
Data Index: 3710358 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.4009. Min Act: -0.1699
Data Index: 3356061 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.4009. Min Act: -0.1697
Data Index: 8131920 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.3833. Min Act: -0.1700
Data Index: 966582 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.3921. Min Act: -0.1700
Data Index: 8703884 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.3921. Min Act: -0.1700
Data Index: 8232405 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.3921. Min Act: -0.1700
Data Index: 4140780 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.3921. Min Act: -0.1700
Data Index: 5248195 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.3833. Min Act: -0.1699
Data Index: 927541 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.3921. Min Act: -0.1700
Data Index: 6058627 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4889. Min Range: -1.4889
Max Act: 1.3833. Min Act: -0.1697
Data Index: 1217855 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19