Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2087. Min Range: -5.2087
Max Act: 5.2087. Min Act: -0.1700
Data Index: 5860852 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2087. Min Range: -5.2087
Max Act: 5.2087. Min Act: -0.1700
Data Index: 1751715 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2087. Min Range: -5.2087
Max Act: 5.1462. Min Act: -0.1700
Data Index: 7681102 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2087. Min Range: -5.2087
Max Act: 5.0837. Min Act: -0.1700
Data Index: 66555 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2087. Min Range: -5.2087
Max Act: 5.0212. Min Act: -0.1700
Data Index: 1673896 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2087. Min Range: -5.2087
Max Act: 5.0525. Min Act: -0.1700
Data Index: 965673 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2087. Min Range: -5.2087
Max Act: 5.0212. Min Act: -0.1700
Data Index: 197089 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2087. Min Range: -5.2087
Max Act: 5.0212. Min Act: -0.1700
Data Index: 4344714 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2087. Min Range: -5.2087
Max Act: 4.9900. Min Act: -0.1700
Data Index: 3199743 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2087. Min Range: -5.2087
Max Act: 4.9900. Min Act: -0.1700
Data Index: 1851237 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2087. Min Range: -5.2087
Max Act: 4.9900. Min Act: -0.1700
Data Index: 7179145 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2087. Min Range: -5.2087
Max Act: 4.9900. Min Act: -0.1700
Data Index: 8070251 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2087. Min Range: -5.2087
Max Act: 5.0212. Min Act: -0.1700
Data Index: 2766730 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2087. Min Range: -5.2087
Max Act: 4.9587. Min Act: -0.1700
Data Index: 4062698 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2087. Min Range: -5.2087
Max Act: 4.9587. Min Act: -0.1700
Data Index: 6146815 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2087. Min Range: -5.2087
Max Act: 4.9275. Min Act: -0.1700
Data Index: 3898317 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2087. Min Range: -5.2087
Max Act: 4.9587. Min Act: -0.1700
Data Index: 1851386 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2087. Min Range: -5.2087
Max Act: 4.9587. Min Act: -0.1700
Data Index: 41786 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2087. Min Range: -5.2087
Max Act: 4.9587. Min Act: -0.1700
Data Index: 2659611 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2087. Min Range: -5.2087
Max Act: 4.9275. Min Act: -0.1700
Data Index: 6309765 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19