Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1656 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.9094. Min Act: -0.1700
Data Index: 2078415 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.8469. Min Act: -0.1700
Data Index: 3148017 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.7844. Min Act: -0.1700
Data Index: 5688106 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.8157. Min Act: -0.1700
Data Index: 7500165 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.7844. Min Act: -0.1700
Data Index: 7936371 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.7844. Min Act: -0.1700
Data Index: 85122 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.7532. Min Act: -0.1700
Data Index: 7420007 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.6907. Min Act: -0.1700
Data Index: 1229146 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.6594. Min Act: -0.1700
Data Index: 5913653 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.6594. Min Act: -0.1700
Data Index: 7594134 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.6907. Min Act: -0.1700
Data Index: 688743 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.6594. Min Act: -0.1700
Data Index: 3479100 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.6594. Min Act: -0.1700
Data Index: 4136361 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.6282. Min Act: -0.1700
Data Index: 3661160 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.6282. Min Act: -0.1700
Data Index: 2207132 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.5969. Min Act: -0.1700
Data Index: 6017432 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.5657. Min Act: -0.1700
Data Index: 8373526 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.5969. Min Act: -0.1700
Data Index: 2059958 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.5657. Min Act: -0.1700
Data Index: 983314 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9094. Min Range: -4.9094
Max Act: 4.5657. Min Act: -0.1700
Data Index: 4115674 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19