Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2147 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.2841. Min Range: -10.2841
Max Act: 10.2841. Min Act: -0.1700
Data Index: 4783595 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2841. Min Range: -10.2841
Max Act: 9.2216. Min Act: -0.1700
Data Index: 2757516 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2841. Min Range: -10.2841
Max Act: 8.6591. Min Act: -0.1700
Data Index: 3696714 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2841. Min Range: -10.2841
Max Act: 8.2216. Min Act: -0.1700
Data Index: 1203880 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2841. Min Range: -10.2841
Max Act: 8.1591. Min Act: -0.1700
Data Index: 8355834 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2841. Min Range: -10.2841
Max Act: 8.1591. Min Act: -0.1700
Data Index: 580641 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.9403. Min Act: -0.1700
Data Index: 988488 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.9091. Min Act: -0.1700
Data Index: 7216957 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.9403. Min Act: -0.1700
Data Index: 3175541 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.8778. Min Act: -0.1700
Data Index: 7193793 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.9091. Min Act: -0.1700
Data Index: 815507 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.8466. Min Act: -0.1700
Data Index: 390666 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.9091. Min Act: -0.1700
Data Index: 3971108 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.8153. Min Act: -0.1700
Data Index: 1750658 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.8466. Min Act: -0.1700
Data Index: 2280455 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.7841. Min Act: -0.1700
Data Index: 7802854 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.6591. Min Act: -0.1700
Data Index: 6927506 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.7216. Min Act: -0.1700
Data Index: 3726045 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.7216. Min Act: -0.1700
Data Index: 6066094 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2841. Min Range: -10.2841
Max Act: 7.6591. Min Act: -0.1700
Data Index: 6802106 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19