Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 736 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1451. Min Range: -9.1451
Max Act: 9.1451. Min Act: -0.1700
Data Index: 1124816 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.9576. Min Act: -0.1700
Data Index: 2589771 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.8951. Min Act: -0.1700
Data Index: 5735419 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.8951. Min Act: -0.1700
Data Index: 8040845 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.7701. Min Act: -0.1700
Data Index: 2231487 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.7701. Min Act: -0.1700
Data Index: 7851134 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.7076. Min Act: -0.1700
Data Index: 363897 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.6451. Min Act: -0.1700
Data Index: 553901 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.6451. Min Act: -0.1700
Data Index: 2310604 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.6451. Min Act: -0.1700
Data Index: 4256207 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.6451. Min Act: -0.1700
Data Index: 3752984 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.5826. Min Act: -0.1700
Data Index: 1616022 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.5826. Min Act: -0.1700
Data Index: 1757965 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.5826. Min Act: -0.1700
Data Index: 4449660 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.5201. Min Act: -0.1700
Data Index: 4781327 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.5826. Min Act: -0.1700
Data Index: 3170064 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.5201. Min Act: -0.1700
Data Index: 7823567 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.5201. Min Act: -0.1700
Data Index: 2735550 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.5201. Min Act: -0.1700
Data Index: 3420085 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1451. Min Range: -9.1451
Max Act: 8.5201. Min Act: -0.1700
Data Index: 237892 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19