Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4450 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.7462. Min Act: -0.1700
Data Index: 6124973 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.6524. Min Act: -0.1700
Data Index: 3677743 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4962. Min Act: -0.1700
Data Index: 3655619 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4962. Min Act: -0.1700
Data Index: 1388172 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4649. Min Act: -0.1700
Data Index: 5959321 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4962. Min Act: -0.1700
Data Index: 921998 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4649. Min Act: -0.1700
Data Index: 1457538 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4649. Min Act: -0.1700
Data Index: 6528262 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4649. Min Act: -0.1700
Data Index: 2232395 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4337. Min Act: -0.1700
Data Index: 7634986 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4337. Min Act: -0.1700
Data Index: 1448847 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4337. Min Act: -0.1700
Data Index: 1798035 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4024. Min Act: -0.1700
Data Index: 7073368 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4024. Min Act: -0.1700
Data Index: 5787111 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.4024. Min Act: -0.1700
Data Index: 3371622 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.3712. Min Act: -0.1700
Data Index: 1305321 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.3712. Min Act: -0.1700
Data Index: 5708438 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.3712. Min Act: -0.1700
Data Index: 8520277 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.3712. Min Act: -0.1700
Data Index: 5515788 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7462. Min Range: -5.7462
Max Act: 5.3399. Min Act: -0.1700
Data Index: 3282720 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19