Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 555 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.8814. Min Act: -0.1700
Data Index: 6168356 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.8502. Min Act: -0.1700
Data Index: 4429014 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.6939. Min Act: -0.1700
Data Index: 2202889 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.6627. Min Act: -0.1700
Data Index: 6936581 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.3814. Min Act: -0.1699
Data Index: 1249225 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.3189. Min Act: -0.1700
Data Index: 1568948 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.0064. Min Act: -0.1700
Data Index: 5051333 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.2564. Min Act: -0.1700
Data Index: 7276057 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.2252. Min Act: -0.1700
Data Index: 4425410 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8814. Min Range: -7.8814
Max Act: 6.2564. Min Act: -0.1700
Data Index: 209592 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.2252. Min Act: -0.1700
Data Index: 8605859 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.2564. Min Act: -0.1700
Data Index: 587012 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.1314. Min Act: -0.1700
Data Index: 1033284 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.1939. Min Act: -0.1700
Data Index: 6997704 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.1627. Min Act: -0.1700
Data Index: 7572996 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.0377. Min Act: -0.1700
Data Index: 891305 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.1314. Min Act: -0.1700
Data Index: 4725308 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.0064. Min Act: -0.1700
Data Index: 2425629 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8814. Min Range: -7.8814
Max Act: 7.0689. Min Act: -0.1700
Data Index: 4000370 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8814. Min Range: -7.8814
Max Act: 6.8502. Min Act: -0.1700
Data Index: 1326682 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19