Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1705 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.8924. Min Act: -0.1700
Data Index: 5988633 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.7986. Min Act: -0.1700
Data Index: 2018751 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.7674. Min Act: -0.1692
Data Index: 7622392 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.7361. Min Act: -0.1700
Data Index: 4385163 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.7361. Min Act: -0.1700
Data Index: 4835008 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.7049. Min Act: -0.1698
Data Index: 3807165 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6736. Min Act: -0.1700
Data Index: 7011290 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6424. Min Act: -0.1700
Data Index: 8289899 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6736. Min Act: -0.1700
Data Index: 2869336 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6736. Min Act: -0.1700
Data Index: 4057758 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6424. Min Act: -0.1699
Data Index: 4635522 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6424. Min Act: -0.1700
Data Index: 198271 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6424. Min Act: -0.1700
Data Index: 4513343 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6424. Min Act: -0.1700
Data Index: 2394566 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6424. Min Act: -0.1700
Data Index: 8071419 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6111. Min Act: -0.1700
Data Index: 4135379 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6111. Min Act: -0.1700
Data Index: 7190448 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6111. Min Act: -0.1700
Data Index: 7799163 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.5799. Min Act: -0.1698
Data Index: 2617452 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8924. Min Range: -4.8924
Max Act: 4.6111. Min Act: -0.1700
Data Index: 2699792 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19