Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1566 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.9124. Min Act: -0.1700
Data Index: 6230502 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.8186. Min Act: -0.1700
Data Index: 8697564 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.7561. Min Act: -0.1700
Data Index: 7623869 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.7561. Min Act: -0.1700
Data Index: 8618297 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.6936. Min Act: -0.1700
Data Index: 8021539 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.6624. Min Act: -0.1700
Data Index: 5721919 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.6624. Min Act: -0.1700
Data Index: 1271229 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.6311. Min Act: -0.1700
Data Index: 3122493 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.6311. Min Act: -0.1700
Data Index: 366609 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.6311. Min Act: -0.1700
Data Index: 5107486 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.6311. Min Act: -0.1700
Data Index: 5379661 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.5686. Min Act: -0.1700
Data Index: 2353596 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.5686. Min Act: -0.1700
Data Index: 632209 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.5374. Min Act: -0.1700
Data Index: 22573 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.5374. Min Act: -0.1700
Data Index: 3039603 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.5374. Min Act: -0.1700
Data Index: 7195856 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.5061. Min Act: -0.1700
Data Index: 3817933 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.5061. Min Act: -0.1700
Data Index: 2580882 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.4749. Min Act: -0.1700
Data Index: 1796313 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9124. Min Range: -4.9124
Max Act: 4.4749. Min Act: -0.1700
Data Index: 3212657 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19