Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.6626. Min Act: -0.1700
Data Index: 8606275 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.5689. Min Act: -0.1700
Data Index: 657973 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.5376. Min Act: -0.1700
Data Index: 6841335 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.5689. Min Act: -0.1700
Data Index: 5118276 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.5376. Min Act: -0.1700
Data Index: 6552771 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.5064. Min Act: -0.1700
Data Index: 7687177 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.5376. Min Act: -0.1700
Data Index: 7258909 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.5064. Min Act: -0.1700
Data Index: 1354044 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.5064. Min Act: -0.1700
Data Index: 408909 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.5064. Min Act: -0.1700
Data Index: 7683340 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.4751. Min Act: -0.1700
Data Index: 7885108 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.5064. Min Act: -0.1700
Data Index: 2547612 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.4439. Min Act: -0.1700
Data Index: 3197823 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.4439. Min Act: -0.1700
Data Index: 7602856 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.4126. Min Act: -0.1700
Data Index: 430024 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.4126. Min Act: -0.1700
Data Index: 5190145 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.4439. Min Act: -0.1700
Data Index: 3025342 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.4126. Min Act: -0.1700
Data Index: 1600542 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.4126. Min Act: -0.1700
Data Index: 7592937 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6626. Min Range: -4.6626
Max Act: 4.4126. Min Act: -0.1700
Data Index: 6925996 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19