Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 540 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1246. Min Range: -5.1246
Max Act: 5.1246. Min Act: -0.1700
Data Index: 1002259 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9684. Min Act: -0.1700
Data Index: 7713765 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9996. Min Act: -0.1700
Data Index: 1369474 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9371. Min Act: -0.1700
Data Index: 882403 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8746. Min Act: -0.1700
Data Index: 331584 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8746. Min Act: -0.1700
Data Index: 1763559 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8746. Min Act: -0.1700
Data Index: 4132376 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8434. Min Act: -0.1700
Data Index: 2240344 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8434. Min Act: -0.1700
Data Index: 429554 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8121. Min Act: -0.1700
Data Index: 7552691 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.7809. Min Act: -0.1700
Data Index: 7411079 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8121. Min Act: -0.1700
Data Index: 4397075 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.7496. Min Act: -0.1700
Data Index: 8494847 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.7809. Min Act: -0.1700
Data Index: 5817952 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.7809. Min Act: -0.1700
Data Index: 3018859 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.7809. Min Act: -0.1700
Data Index: 476155 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.7809. Min Act: -0.1700
Data Index: 6500024 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.7809. Min Act: -0.1700
Data Index: 2522054 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.7809. Min Act: -0.1700
Data Index: 6308342 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.7809. Min Act: -0.1700
Data Index: 554953 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19