Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 90 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.6072. Min Act: -0.1700
Data Index: 6461082 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.6384. Min Act: -0.1700
Data Index: 1963093 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.5447. Min Act: -0.1700
Data Index: 4830522 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.5447. Min Act: -0.1700
Data Index: 1454690 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.5447. Min Act: -0.1700
Data Index: 4235920 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.5447. Min Act: -0.1700
Data Index: 891367 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.5447. Min Act: -0.1700
Data Index: 56726 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.4509. Min Act: -0.1700
Data Index: 2642801 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.5134. Min Act: -0.1700
Data Index: 789425 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.4822. Min Act: -0.1700
Data Index: 3256218 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.4822. Min Act: -0.1700
Data Index: 794793 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.4822. Min Act: -0.1700
Data Index: 3531201 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.4822. Min Act: -0.1700
Data Index: 4033667 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.4509. Min Act: -0.1700
Data Index: 7787240 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.4509. Min Act: -0.1700
Data Index: 1419839 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.4197. Min Act: -0.1700
Data Index: 7980740 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.4509. Min Act: -0.1700
Data Index: 2404648 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.4509. Min Act: -0.1700
Data Index: 752972 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.4509. Min Act: -0.1700
Data Index: 6440516 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6384. Min Range: -4.6384
Max Act: 4.4197. Min Act: -0.1700
Data Index: 3072300 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19