Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4047 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2633. Min Range: -7.2633
Max Act: 7.2320. Min Act: -0.1700
Data Index: 3107737 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2633. Min Range: -7.2633
Max Act: 7.2633. Min Act: -0.1700
Data Index: 6675765 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2633. Min Range: -7.2633
Max Act: 7.0445. Min Act: -0.1700
Data Index: 2135241 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.9820. Min Act: -0.1700
Data Index: 8735066 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.8883. Min Act: -0.1700
Data Index: 8583453 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.8570. Min Act: -0.1700
Data Index: 783910 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.7945. Min Act: -0.1700
Data Index: 7902034 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.7633. Min Act: -0.1700
Data Index: 8059213 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.7633. Min Act: -0.1700
Data Index: 1600236 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.7320. Min Act: -0.1700
Data Index: 4015725 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.7008. Min Act: -0.1700
Data Index: 8309907 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.7008. Min Act: -0.1700
Data Index: 2303480 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.7008. Min Act: -0.1700
Data Index: 1742880 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.6070. Min Act: -0.1700
Data Index: 433133 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.6695. Min Act: -0.1700
Data Index: 3641037 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.6383. Min Act: -0.1700
Data Index: 6461677 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.6383. Min Act: -0.1700
Data Index: 7404601 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.6383. Min Act: -0.1700
Data Index: 6084607 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.5758. Min Act: -0.1700
Data Index: 5613942 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2633. Min Range: -7.2633
Max Act: 6.5758. Min Act: -0.1700
Data Index: 4181528 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19