Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2710. Min Range: -5.2710
Max Act: 5.2710. Min Act: -0.1700
Data Index: 2282501 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2710. Min Range: -5.2710
Max Act: 5.0835. Min Act: -0.1700
Data Index: 4824242 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2710. Min Range: -5.2710
Max Act: 5.0523. Min Act: -0.1700
Data Index: 8007317 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.9898. Min Act: -0.1700
Data Index: 3452194 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.9273. Min Act: -0.1700
Data Index: 6221839 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.9273. Min Act: -0.1700
Data Index: 1415842 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.9273. Min Act: -0.1700
Data Index: 1674373 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.8960. Min Act: -0.1700
Data Index: 4487248 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.8960. Min Act: -0.1700
Data Index: 5827135 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.8960. Min Act: -0.1700
Data Index: 3916686 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.8648. Min Act: -0.1700
Data Index: 5631354 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.8335. Min Act: -0.1700
Data Index: 6647852 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.8023. Min Act: -0.1700
Data Index: 2068706 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.8335. Min Act: -0.1700
Data Index: 6606672 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.7710. Min Act: -0.1700
Data Index: 5947513 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.8023. Min Act: -0.1700
Data Index: 174231 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.8023. Min Act: -0.1700
Data Index: 3410716 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.8023. Min Act: -0.1700
Data Index: 2185739 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.8023. Min Act: -0.1700
Data Index: 5389197 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2710. Min Range: -5.2710
Max Act: 4.8023. Min Act: -0.1700
Data Index: 533334 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19