Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1865 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.9454. Min Act: -0.1700
Data Index: 4674757 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.7267. Min Act: -0.1700
Data Index: 2385969 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6954. Min Act: -0.1700
Data Index: 7719147 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6642. Min Act: -0.1700
Data Index: 8362752 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6954. Min Act: -0.1700
Data Index: 6806969 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6329. Min Act: -0.1700
Data Index: 4421016 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6329. Min Act: -0.1700
Data Index: 6105331 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6017. Min Act: -0.1700
Data Index: 5923917 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6017. Min Act: -0.1700
Data Index: 4284317 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5079. Min Act: -0.1700
Data Index: 5072453 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5392. Min Act: -0.1700
Data Index: 7693099 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5392. Min Act: -0.1700
Data Index: 2095858 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5079. Min Act: -0.1700
Data Index: 4318396 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5079. Min Act: -0.1700
Data Index: 1140201 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5079. Min Act: -0.1700
Data Index: 3823397 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5079. Min Act: -0.1700
Data Index: 2913246 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.4454. Min Act: -0.1700
Data Index: 3414154 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.4767. Min Act: -0.1700
Data Index: 7705510 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.4767. Min Act: -0.1700
Data Index: 3130404 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.4454. Min Act: -0.1700
Data Index: 3322792 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19