Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1661 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.3187. Min Act: -0.1700
Data Index: 166638 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.2250. Min Act: -0.1700
Data Index: 6062372 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.2562. Min Act: -0.1700
Data Index: 2635506 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.2250. Min Act: -0.1700
Data Index: 6051478 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1937. Min Act: -0.1700
Data Index: 2447131 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1625. Min Act: -0.1700
Data Index: 7089133 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1625. Min Act: -0.1700
Data Index: 1709135 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1312. Min Act: -0.1700
Data Index: 7268100 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1625. Min Act: -0.1700
Data Index: 3414500 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1000. Min Act: -0.1700
Data Index: 751006 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1000. Min Act: -0.1700
Data Index: 4588032 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1312. Min Act: -0.1700
Data Index: 8430708 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1000. Min Act: -0.1700
Data Index: 8222614 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1000. Min Act: -0.1700
Data Index: 3438490 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1000. Min Act: -0.1700
Data Index: 1127847 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1000. Min Act: -0.1700
Data Index: 5440411 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.0687. Min Act: -0.1700
Data Index: 1246585 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.1000. Min Act: -0.1700
Data Index: 8283213 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.0375. Min Act: -0.1700
Data Index: 1754024 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3187. Min Range: -5.3187
Max Act: 5.0375. Min Act: -0.1700
Data Index: 4448971 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19