Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 733 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.9698. Min Act: -0.1700
Data Index: 1581608 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.9386. Min Act: -0.1700
Data Index: 2600803 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.8136. Min Act: -0.1700
Data Index: 870127 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.7823. Min Act: -0.1700
Data Index: 7604555 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.7511. Min Act: -0.1700
Data Index: 4181682 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.7198. Min Act: -0.1700
Data Index: 6897874 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.7511. Min Act: -0.1700
Data Index: 1740099 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.7198. Min Act: -0.1700
Data Index: 4655278 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.6886. Min Act: -0.1700
Data Index: 524318 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.6886. Min Act: -0.1700
Data Index: 7898589 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.6573. Min Act: -0.1700
Data Index: 6633818 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.6573. Min Act: -0.1700
Data Index: 5918246 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.6261. Min Act: -0.1700
Data Index: 2045680 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.6573. Min Act: -0.1700
Data Index: 7934023 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.5636. Min Act: -0.1700
Data Index: 3358378 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.5636. Min Act: -0.1700
Data Index: 713314 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.5636. Min Act: -0.1700
Data Index: 2658655 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.5636. Min Act: -0.1700
Data Index: 8018247 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.5636. Min Act: -0.1700
Data Index: 2229880 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9698. Min Range: -5.9698
Max Act: 5.5323. Min Act: -0.1700
Data Index: 6459307 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19