Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3946 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1448. Min Range: -8.1448
Max Act: 8.1448. Min Act: -0.1700
Data Index: 2167795 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1448. Min Range: -8.1448
Max Act: 8.0823. Min Act: -0.1700
Data Index: 5261820 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1448. Min Range: -8.1448
Max Act: 8.0198. Min Act: -0.1700
Data Index: 8760066 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.9573. Min Act: -0.1700
Data Index: 2751498 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.9573. Min Act: -0.1700
Data Index: 2663967 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.9573. Min Act: -0.1700
Data Index: 3139744 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1448. Min Range: -8.1448
Max Act: 8.0198. Min Act: -0.1700
Data Index: 5527200 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.8323. Min Act: -0.1700
Data Index: 6415392 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.8948. Min Act: -0.1700
Data Index: 5597083 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.8948. Min Act: -0.1700
Data Index: 7901220 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.8323. Min Act: -0.1700
Data Index: 7033444 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.7698. Min Act: -0.1700
Data Index: 3159244 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.7698. Min Act: -0.1700
Data Index: 4345147 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.7698. Min Act: -0.1700
Data Index: 526621 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.7698. Min Act: -0.1700
Data Index: 7610513 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.7385. Min Act: -0.1700
Data Index: 4348225 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.7385. Min Act: -0.1700
Data Index: 6913649 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.7073. Min Act: -0.1700
Data Index: 8739779 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.7073. Min Act: -0.1700
Data Index: 2201526 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1448. Min Range: -8.1448
Max Act: 7.6760. Min Act: -0.1700
Data Index: 465470 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19