Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3933 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6580. Min Range: -6.6580
Max Act: 6.6580. Min Act: -0.1700
Data Index: 208282 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6580. Min Range: -6.6580
Max Act: 6.5017. Min Act: -0.1700
Data Index: 6555456 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6580. Min Range: -6.6580
Max Act: 6.2205. Min Act: -0.1700
Data Index: 1366616 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6580. Min Range: -6.6580
Max Act: 6.1267. Min Act: -0.1700
Data Index: 1036133 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6580. Min Range: -6.6580
Max Act: 6.0642. Min Act: -0.1700
Data Index: 7556170 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6580. Min Range: -6.6580
Max Act: 6.0642. Min Act: -0.1700
Data Index: 4592345 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6580. Min Range: -6.6580
Max Act: 6.0642. Min Act: -0.1700
Data Index: 8756283 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6580. Min Range: -6.6580
Max Act: 5.9392. Min Act: -0.1700
Data Index: 7761458 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6580. Min Range: -6.6580
Max Act: 6.0017. Min Act: -0.1700
Data Index: 802551 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6580. Min Range: -6.6580
Max Act: 5.9392. Min Act: -0.1700
Data Index: 4661693 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6580. Min Range: -6.6580
Max Act: 5.9392. Min Act: -0.1700
Data Index: 3313987 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6580. Min Range: -6.6580
Max Act: 5.9392. Min Act: -0.1700
Data Index: 530316 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6580. Min Range: -6.6580
Max Act: 5.8455. Min Act: -0.1700
Data Index: 5123142 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6580. Min Range: -6.6580
Max Act: 5.8767. Min Act: -0.1700
Data Index: 503792 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6580. Min Range: -6.6580
Max Act: 5.8455. Min Act: -0.1700
Data Index: 354934 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6580. Min Range: -6.6580
Max Act: 5.8767. Min Act: -0.1700
Data Index: 3488547 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6580. Min Range: -6.6580
Max Act: 5.8455. Min Act: -0.1700
Data Index: 807096 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6580. Min Range: -6.6580
Max Act: 5.8455. Min Act: -0.1700
Data Index: 1494189 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6580. Min Range: -6.6580
Max Act: 5.8455. Min Act: -0.1700
Data Index: 2555532 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6580. Min Range: -6.6580
Max Act: 5.8142. Min Act: -0.1700
Data Index: 227071 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19