Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2644 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1046. Min Range: -5.1046
Max Act: 5.0733. Min Act: -0.1699
Data Index: 2683439 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1046. Min Range: -5.1046
Max Act: 5.0733. Min Act: -0.1700
Data Index: 5967169 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1046. Min Range: -5.1046
Max Act: 5.1046. Min Act: -0.1700
Data Index: 5002129 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1046. Min Range: -5.1046
Max Act: 5.0108. Min Act: -0.1700
Data Index: 656705 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1046. Min Range: -5.1046
Max Act: 5.0108. Min Act: -0.1700
Data Index: 6920947 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.8858. Min Act: -0.1700
Data Index: 4751958 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.9483. Min Act: -0.1700
Data Index: 106464 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.9171. Min Act: -0.1700
Data Index: 5002125 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.8858. Min Act: -0.1699
Data Index: 1754673 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.8858. Min Act: -0.1700
Data Index: 6181773 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.8546. Min Act: -0.1700
Data Index: 2275144 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.8546. Min Act: -0.1700
Data Index: 619432 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.8233. Min Act: -0.1700
Data Index: 429729 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.8546. Min Act: -0.1700
Data Index: 5652990 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.8546. Min Act: -0.1700
Data Index: 8099447 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.8233. Min Act: -0.1700
Data Index: 6748340 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.8233. Min Act: -0.1700
Data Index: 6837820 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.7921. Min Act: -0.1700
Data Index: 5001600 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.7921. Min Act: -0.1700
Data Index: 6692528 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1046. Min Range: -5.1046
Max Act: 4.7608. Min Act: -0.1700
Data Index: 3055015 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19