Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3775 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2134. Min Range: -5.2134
Max Act: 5.2134. Min Act: -0.1700
Data Index: 4832125 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2134. Min Range: -5.2134
Max Act: 5.2134. Min Act: -0.1700
Data Index: 4832141 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2134. Min Range: -5.2134
Max Act: 5.1821. Min Act: -0.1700
Data Index: 7649327 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.9321. Min Act: -0.1700
Data Index: 4955849 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.9634. Min Act: -0.1700
Data Index: 568428 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.9009. Min Act: -0.1700
Data Index: 4832131 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.9009. Min Act: -0.1700
Data Index: 312467 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.9009. Min Act: -0.1700
Data Index: 3106737 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.8384. Min Act: -0.1700
Data Index: 4621481 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.8696. Min Act: -0.1700
Data Index: 446483 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.8696. Min Act: -0.1700
Data Index: 4832147 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.8384. Min Act: -0.1700
Data Index: 2165811 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.8071. Min Act: -0.1700
Data Index: 236248 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.8696. Min Act: -0.1700
Data Index: 1212597 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.8384. Min Act: -0.1700
Data Index: 86773 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.8384. Min Act: -0.1700
Data Index: 8731548 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.8696. Min Act: -0.1700
Data Index: 6874551 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.8384. Min Act: -0.1700
Data Index: 1153944 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.8384. Min Act: -0.1700
Data Index: 86801 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2134. Min Range: -5.2134
Max Act: 4.7759. Min Act: -0.1700
Data Index: 4246476 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19