Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2503 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0945. Min Range: -5.0945
Max Act: 5.0945. Min Act: -0.1700
Data Index: 7530970 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0945. Min Range: -5.0945
Max Act: 5.0007. Min Act: -0.1700
Data Index: 258686 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.9382. Min Act: -0.1700
Data Index: 6919650 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.9695. Min Act: -0.1700
Data Index: 7073647 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.9695. Min Act: -0.1700
Data Index: 2901373 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.9695. Min Act: -0.1700
Data Index: 231475 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.9382. Min Act: -0.1700
Data Index: 139619 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.8757. Min Act: -0.1700
Data Index: 6379637 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.9070. Min Act: -0.1700
Data Index: 3228170 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.8757. Min Act: -0.1700
Data Index: 6805660 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.8757. Min Act: -0.1700
Data Index: 6379635 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.8132. Min Act: -0.1700
Data Index: 6379636 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.8445. Min Act: -0.1700
Data Index: 2666295 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.8445. Min Act: -0.1700
Data Index: 3321072 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.8445. Min Act: -0.1700
Data Index: 137002 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.8445. Min Act: -0.1700
Data Index: 7489883 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.7820. Min Act: -0.1700
Data Index: 7945773 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.8445. Min Act: -0.1700
Data Index: 4359697 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.7820. Min Act: -0.1700
Data Index: 231474 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0945. Min Range: -5.0945
Max Act: 4.8132. Min Act: -0.1700
Data Index: 6027048 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19