Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1760 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.5580. Min Act: -0.1700
Data Index: 1510837 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.4017. Min Act: -0.1700
Data Index: 7543526 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.3392. Min Act: -0.1700
Data Index: 775106 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.2455. Min Act: -0.1700
Data Index: 5517732 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.2455. Min Act: -0.1700
Data Index: 8083064 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.2455. Min Act: -0.1700
Data Index: 6671071 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.1830. Min Act: -0.1700
Data Index: 3005305 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.1517. Min Act: -0.1700
Data Index: 5399945 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.1517. Min Act: -0.1700
Data Index: 698129 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.1517. Min Act: -0.1700
Data Index: 7512757 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.1517. Min Act: -0.1700
Data Index: 357184 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.1517. Min Act: -0.1700
Data Index: 4246327 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.1205. Min Act: -0.1700
Data Index: 1141875 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.0892. Min Act: -0.1700
Data Index: 7445586 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.1205. Min Act: -0.1700
Data Index: 3397476 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.0892. Min Act: -0.1700
Data Index: 8375592 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.0579. Min Act: -0.1700
Data Index: 8101860 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.0579. Min Act: -0.1700
Data Index: 972387 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.0579. Min Act: -0.1700
Data Index: 846893 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5580. Min Range: -4.5580
Max Act: 4.0579. Min Act: -0.1700
Data Index: 1854313 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19