Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 280 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.9270. Min Act: -0.1700
Data Index: 24235 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.9270. Min Act: -0.1700
Data Index: 3730642 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.8332. Min Act: -0.1700
Data Index: 7356006 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.7082. Min Act: -0.1700
Data Index: 5571592 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.6145. Min Act: -0.1699
Data Index: 485892 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.6145. Min Act: -0.1700
Data Index: 2420761 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.5832. Min Act: -0.1700
Data Index: 4320700 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.5832. Min Act: -0.1700
Data Index: 2420762 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.5520. Min Act: -0.1700
Data Index: 6160894 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.5520. Min Act: -0.1700
Data Index: 5908124 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.5207. Min Act: -0.1700
Data Index: 1744238 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.5207. Min Act: -0.1697
Data Index: 8559557 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.5207. Min Act: -0.1700
Data Index: 5071034 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.4895. Min Act: -0.1700
Data Index: 6157012 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.5207. Min Act: -0.1700
Data Index: 1317700 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.5207. Min Act: -0.1698
Data Index: 3426091 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.4895. Min Act: -0.1700
Data Index: 3731456 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.5207. Min Act: -0.1700
Data Index: 572793 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.4582. Min Act: -0.1700
Data Index: 615927 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9270. Min Range: -5.9270
Max Act: 5.4582. Min Act: -0.1700
Data Index: 8071687 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19