Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 648 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.8256. Min Act: -0.1700
Data Index: 3707287 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.7006. Min Act: -0.1700
Data Index: 6520817 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.7006. Min Act: -0.1700
Data Index: 3886322 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.7006. Min Act: -0.1700
Data Index: 531479 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.6693. Min Act: -0.1700
Data Index: 6897590 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.6381. Min Act: -0.1700
Data Index: 1717186 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.6381. Min Act: -0.1700
Data Index: 8686877 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.6381. Min Act: -0.1700
Data Index: 6382731 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.6381. Min Act: -0.1700
Data Index: 3422172 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.6068. Min Act: -0.1700
Data Index: 1649065 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.5443. Min Act: -0.1700
Data Index: 4964384 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.5756. Min Act: -0.1700
Data Index: 7960046 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.5756. Min Act: -0.1700
Data Index: 6049855 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.5443. Min Act: -0.1700
Data Index: 5363349 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.5756. Min Act: -0.1700
Data Index: 8157950 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.5443. Min Act: -0.1700
Data Index: 1231816 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.5131. Min Act: -0.1700
Data Index: 4114400 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.5443. Min Act: -0.1700
Data Index: 1330667 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.5131. Min Act: -0.1700
Data Index: 3867413 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8256. Min Range: -4.8256
Max Act: 4.4818. Min Act: -0.1700
Data Index: 149638 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19