Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1581 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.7217. Min Act: -0.1700
Data Index: 2248433 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.7529. Min Act: -0.1700
Data Index: 3722446 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.7217. Min Act: -0.1700
Data Index: 5140365 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.6904. Min Act: -0.1700
Data Index: 5163144 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.6904. Min Act: -0.1700
Data Index: 1160515 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.6592. Min Act: -0.1700
Data Index: 21302 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.6592. Min Act: -0.1700
Data Index: 2486394 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.6279. Min Act: -0.1700
Data Index: 2336434 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.6592. Min Act: -0.1700
Data Index: 1515420 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.5654. Min Act: -0.1700
Data Index: 3107543 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.4717. Min Act: -0.1700
Data Index: 3650711 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.5029. Min Act: -0.1700
Data Index: 6362560 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.5029. Min Act: -0.1700
Data Index: 301565 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.5029. Min Act: -0.1700
Data Index: 3674231 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.3779. Min Act: -0.1700
Data Index: 613353 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.4404. Min Act: -0.1700
Data Index: 3396182 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.3779. Min Act: -0.1700
Data Index: 8659777 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.3779. Min Act: -0.1700
Data Index: 6259448 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.3779. Min Act: -0.1700
Data Index: 8018528 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7529. Min Range: -5.7529
Max Act: 5.3779. Min Act: -0.1700
Data Index: 2674867 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19