Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 638 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.4018. Min Act: -0.1700
Data Index: 6567328 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.4331. Min Act: -0.1700
Data Index: 497158 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.3393. Min Act: -0.1700
Data Index: 3688150 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.3081. Min Act: -0.1700
Data Index: 2438697 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.2768. Min Act: -0.1700
Data Index: 1279994 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.2143. Min Act: -0.1700
Data Index: 6040509 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.1831. Min Act: -0.1700
Data Index: 2090382 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.1518. Min Act: -0.1700
Data Index: 6873639 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.0893. Min Act: -0.1700
Data Index: 1354132 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.0893. Min Act: -0.1700
Data Index: 5570041 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.0581. Min Act: -0.1700
Data Index: 164641 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.0581. Min Act: -0.1700
Data Index: 2032857 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.0581. Min Act: -0.1700
Data Index: 7135698 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.0268. Min Act: -0.1700
Data Index: 3222988 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4331. Min Range: -5.4331
Max Act: 4.9956. Min Act: -0.1700
Data Index: 1358257 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4331. Min Range: -5.4331
Max Act: 4.9956. Min Act: -0.1700
Data Index: 1044622 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4331. Min Range: -5.4331
Max Act: 5.0268. Min Act: -0.1700
Data Index: 3387226 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4331. Min Range: -5.4331
Max Act: 4.9643. Min Act: -0.1700
Data Index: 4766208 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4331. Min Range: -5.4331
Max Act: 4.9643. Min Act: -0.1700
Data Index: 919174 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4331. Min Range: -5.4331
Max Act: 4.9643. Min Act: -0.1700
Data Index: 4415553 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19