Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1628. Min Range: -6.1628
Max Act: 6.1628. Min Act: -0.1700
Data Index: 35243 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1628. Min Range: -6.1628
Max Act: 6.1003. Min Act: -0.1700
Data Index: 7556730 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1628. Min Range: -6.1628
Max Act: 6.0690. Min Act: -0.1700
Data Index: 3768445 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.8815. Min Act: -0.1700
Data Index: 3413035 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.8503. Min Act: -0.1700
Data Index: 411610 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.8503. Min Act: -0.1700
Data Index: 1578441 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.8190. Min Act: -0.1700
Data Index: 1600712 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.8503. Min Act: -0.1700
Data Index: 368736 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.8190. Min Act: -0.1700
Data Index: 3696439 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.8190. Min Act: -0.1700
Data Index: 5206097 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.7878. Min Act: -0.1700
Data Index: 476329 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.7878. Min Act: -0.1700
Data Index: 7694452 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.7565. Min Act: -0.1700
Data Index: 3040213 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.7565. Min Act: -0.1700
Data Index: 915293 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.6940. Min Act: -0.1700
Data Index: 4690525 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.7253. Min Act: -0.1700
Data Index: 7753154 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.7253. Min Act: -0.1700
Data Index: 3786198 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.6940. Min Act: -0.1700
Data Index: 3563049 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.6940. Min Act: -0.1700
Data Index: 1929839 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1628. Min Range: -6.1628
Max Act: 5.6628. Min Act: -0.1700
Data Index: 4098793 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19