Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3073 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.9369. Min Act: -0.1700
Data Index: 2969519 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.9057. Min Act: -0.1700
Data Index: 3385225 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.9057. Min Act: -0.1700
Data Index: 8237937 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.8432. Min Act: -0.1700
Data Index: 7157832 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.7807. Min Act: -0.1700
Data Index: 5575560 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.7807. Min Act: -0.1700
Data Index: 559488 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.7182. Min Act: -0.1700
Data Index: 8689474 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.6869. Min Act: -0.1700
Data Index: 4256088 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.6869. Min Act: -0.1700
Data Index: 995447 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.6557. Min Act: -0.1700
Data Index: 1664034 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.5932. Min Act: -0.1700
Data Index: 3104188 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.6244. Min Act: -0.1700
Data Index: 4504079 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.5932. Min Act: -0.1700
Data Index: 3873194 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.6244. Min Act: -0.1700
Data Index: 300522 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.6244. Min Act: -0.1700
Data Index: 2574794 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.5932. Min Act: -0.1700
Data Index: 3056507 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.5932. Min Act: -0.1700
Data Index: 6331606 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.5619. Min Act: -0.1700
Data Index: 8164777 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.5619. Min Act: -0.1700
Data Index: 5401992 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9369. Min Range: -6.9369
Max Act: 6.5619. Min Act: -0.1700
Data Index: 6260391 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19