Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3691 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.9497. Min Act: -0.1700
Data Index: 3142097 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.9497. Min Act: -0.1700
Data Index: 7962403 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.9185. Min Act: -0.1700
Data Index: 7113595 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.9185. Min Act: -0.1700
Data Index: 3102161 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.8872. Min Act: -0.1700
Data Index: 2122395 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.8560. Min Act: -0.1700
Data Index: 7712264 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.8872. Min Act: -0.1700
Data Index: 3782299 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.7935. Min Act: -0.1700
Data Index: 6114775 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.7935. Min Act: -0.1700
Data Index: 5849399 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.7622. Min Act: -0.1700
Data Index: 8607312 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.7310. Min Act: -0.1700
Data Index: 6276146 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.7310. Min Act: -0.1700
Data Index: 4745188 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.7310. Min Act: -0.1700
Data Index: 2320506 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6997. Min Act: -0.1700
Data Index: 269782 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6685. Min Act: -0.1700
Data Index: 2519696 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6997. Min Act: -0.1700
Data Index: 3669426 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6997. Min Act: -0.1700
Data Index: 5851929 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6997. Min Act: -0.1700
Data Index: 7558558 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6997. Min Act: -0.1700
Data Index: 1284638 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9497. Min Range: -5.9497
Max Act: 5.6997. Min Act: -0.1700
Data Index: 3540346 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19